Head-to-head comparison
GPT-5.6 Sol vs. GPT-5.6 Luna
Compare published benchmark results from matching versions and cohorts, API pricing, and technical specifications. Any documented test setup differences remain visible.
216
shared result series
30
distinct benchmarks
2026-08-16
latest retrieval
Change model selection
Specifications and cost
General specifications and standard API pricing
Undisclosed parameter counts and knowledge cutoffs stay marked as unavailable. The table shows direct standard token pricing, including documented context tiers. Batch, fast, priority, regional surcharges, tool calls, and cloud platform pricing are excluded.
| Attribute | GPT-5.6 Sol | GPT-5.6 Luna |
|---|---|---|
| Provider | OpenAI | OpenAI |
| Released | Jun 26, 2026 | Jun 26, 2026 |
| Availability | Active | Active |
| Model type | Proprietary | Proprietary |
| Parameters | Not published | Not published |
| Architecture | Not published | Not published |
| Context window | 1,050,000 tokens | 1,050,000 tokens |
| Knowledge cutoff | February 16, 2026 | February 16, 2026 |
| Technical sources | Model, Context, Knowledge cutoff | Model, Context, Knowledge cutoff |
| API pricing per 1M tokens | ||
| API input | $5 ≤272K / $10 >272K | $0.2 ≤272K / $0.4 >272K |
| API output | $30 ≤272K / $45 >272K | $1.2 ≤272K / $1.8 >272K |
| Cache read | $0.5 ≤272K / $1 >272K | $0.02 ≤272K / $0.04 >272K |
| Cache write (5 min.) | $6.25 ≤272K / $12.5 >272K | $0.25 ≤272K / $0.5 >272K |
| Cache write (1 hr.) | Not listed | Not listed |
| Price verified | 08/11/2026Source | 08/11/2026Source |
GPT-5.6 SolGPT-5.6 Luna
API inputUSD per 1M tokens, base tier
GPT-5.6 Sol$5
GPT-5.6 Luna$0.2Lower price
API outputUSD per 1M tokens, base tier
GPT-5.6 Sol$30
GPT-5.6 Luna$1.2Lower price
Cache readUSD per 1M tokens, base tier
GPT-5.6 Sol$0.5
GPT-5.6 Luna$0.02Lower price
Performance
Shared benchmarks
Only published results with the same benchmark version, task, metric, and comparison cohort are paired. Different reasoning levels, agents, harnesses, or output limits appear directly in the table.
216 shared result series
GPT-5.6 SolGPT-5.6 Luna
ARC-AGI-2Overall. Higher is better. No documented setup difference
GPT-5.6 Sol85.4 %Winner
GPT-5.6 Luna29.3 %
ARC-AGI-3RHAE overall score. Higher is better. Test setup not documented as identical
GPT-5.6 Sol2.15 %Higher measured value
GPT-5.6 Luna0.18 %
Arena Text, Style ControlOverall. Higher is better. No documented setup difference
GPT-5.6 Sol1,480.992 arena pointsWinner
GPT-5.6 Luna1,450.561 arena points
BrowseCompOverall. Higher is better. No documented setup difference
GPT-5.6 Sol90.4 %Winner
GPT-5.6 Luna83.3 %
Code MigrationOverall. Higher is better. No documented setup difference
GPT-5.6 Sol52.916 %Winner
GPT-5.6 Luna44.55 %
CorpFin v2Overall. Higher is better. No documented setup difference
GPT-5.6 Sol64.375 %Winner
GPT-5.6 Luna64.219 %
CyberBenchOverall. Higher is better. No documented setup difference
GPT-5.6 Sol88.136 %Winner
GPT-5.6 Luna83.898 %
EMBOverall. Higher is better. No documented setup difference
GPT-5.6 Sol72.339 %Winner
GPT-5.6 Luna67.116 %
Finance Agent (v2)Overall. Higher is better. No documented setup difference
GPT-5.6 Sol53.756 %
GPT-5.6 Luna55.044 %Winner
GPQA DiamondOverall. Higher is better. No documented setup difference
GPT-5.6 Sol95.202 %Winner
GPT-5.6 Luna91.666 %
Harvey's Legal Agent BenchmarkOverall · Task fully resolved. Higher is better. No documented setup difference
GPT-5.6 Sol2.5 %Winner
GPT-5.6 Luna1.25 %
IOIOverall. Higher is better. No documented setup difference
GPT-5.6 Sol86.667 %Winner
GPT-5.6 Luna72.917 %
| Benchmark and task | GPT-5.6 Sol | GPT-5.6 Luna | Comparability | Source |
|---|---|---|---|---|
| ARC-AGI-2OverallReasoning: high | 85.4 %Winner | 29.3 % | 2exact task accuracyHigher is betterCohort: arc-agi-2-gpt-5-6-reasoning-sweepNo documented setup differenceWinner: GPT-5.6 SolGPT-5.6 Sol: Reasoning: high, Attempts: two exact output guesses per task GPT-5.6 Luna: Reasoning: high, Attempts: two exact output guesses per taskThe same verified test with five reasoning levels per model. | ARC PrizeType: Official benchmark leaderboardLeaderboard updated: 2026-07-09Import ID: curated-arc-prize-2026-08-02-7a96b42a4263 / curated-arc-prize-2026-08-02-ef39cd78907eRetrieved 2026-08-02 |
| ARC-AGI-3RHAE overall score | 2.15 %Higher measured value | 0.18 % | ARC-AGI-3 2026 verifiedRHAE scoreHigher is betterCohort: arc-agi-3-semi-private-verified-official-harnessTest setup not documented as identicalNo direct winnerGPT-5.6 Sol: Reasoning: high, Agent: ARC Prize official harness, Harness: ARC Prize official harness GPT-5.6 Luna: Reasoning: max, Agent: ARC Prize official harness, Harness: ARC Prize official harnessOfficial ARC Prize harness on unseen interactive environments. Reasoning levels remain separate. | ARC PrizeType: Official benchmark leaderboardImport ID: curated-arc-prize-2026-08-06-7f3603da855a / curated-arc-prize-2026-08-06-7d499fffd2c4Retrieved 2026-08-06 |
| Arena Text, Style ControlOverallReasoning: xhigh | 1,480.992 arena pointsWinner 95% confidence interval: ±5.733The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | 1,450.561 arena points 95% confidence interval: ±5.636The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | style-control-v1style-controlled Bradley-Terry ratingHigher is betterCohort: lmarena-text-style-control:2026-08-12:overallNo documented setup differenceWinner: GPT-5.6 SolGPT-5.6 Sol: Snapshot: gpt-5.6-sol-xhigh, Reasoning: xhigh, Harness: Arena text, style control GPT-5.6 Luna: Snapshot: gpt-5.6-luna-xhigh, Reasoning: xhigh, Harness: Arena text, style controlGPT-5.6 Sol: Style-controlled Arena rating from 15,450 anonymous pairwise votes.GPT-5.6 Luna: Style-controlled Arena rating from 16,419 anonymous pairwise votes. | ArenaType: Official benchmark leaderboardLeaderboard updated: 2026-08-12Import ID: lmarena-eeedf9209373a7f9b324bfb839e7b02fedacd1e5-1611ed64f3f1Retrieved 2026-08-16 |
| BrowseCompOverall | 90.4 %Winner Editorial selection from the vendor table, not a complete extract of the comparison cohort. | 83.3 % Editorial selection from the vendor table, not a complete extract of the comparison cohort. | 1,266 tasksaccuracyHigher is betterCohort: browsecomp-openai-gpt-5-6-tableNo documented setup differenceWinner: GPT-5.6 SolGPT-5.6 Sol: No further settings disclosed GPT-5.6 Luna: No further settings disclosedCross-vendor comparison table with browsing tools. Exact agent systems differ. | OpenAIType: Vendor-reportedLeaderboard updated: 2026-07-09Import ID: curated-openai-2026-08-02-3d2469516088 / curated-openai-2026-08-02-65d8d2d5bbb4Retrieved 2026-08-02 |
| Code MigrationOverall | 52.916 %Winner | 44.55 % | 1accuracyHigher is betterCohort: vals-code-migration:1:overallNo documented setup differenceWinner: GPT-5.6 SolGPT-5.6 Sol: No further settings disclosed GPT-5.6 Luna: No further settings disclosed | Vals AIType: Independent evaluationLeaderboard updated: 2026-08-13Import ID: vals-code-migration-2026-08-16-107652dc6bfcRetrieved 2026-08-16 |
| CorpFin v2Overall | 64.375 %Winner | 64.219 % | 2accuracyHigher is betterCohort: vals-corp-fin-v2:2:overallNo documented setup differenceWinner: GPT-5.6 SolGPT-5.6 Sol: No further settings disclosed GPT-5.6 Luna: No further settings disclosed | Vals AIType: Independent evaluationLeaderboard updated: 2026-08-12Import ID: vals-corp_fin_v2-2026-08-16-45bbf84f57abRetrieved 2026-08-16 |
| CyberBenchOverall | 88.136 %Winner | 83.898 % | 1accuracyHigher is betterCohort: vals-cyberbench:1:overallNo documented setup differenceWinner: GPT-5.6 SolGPT-5.6 Sol: No further settings disclosed GPT-5.6 Luna: No further settings disclosed | Vals AIType: Independent evaluationLeaderboard updated: 2026-08-03Import ID: vals-cyber-2026-08-16-702acaee9aa9Retrieved 2026-08-16 |
| EMBOverall | 72.339 %Winner | 67.116 % | 1accuracyHigher is betterCohort: vals-emb:1:overallNo documented setup differenceWinner: GPT-5.6 SolGPT-5.6 Sol: No further settings disclosed GPT-5.6 Luna: No further settings disclosed | Vals AIType: Independent evaluationLeaderboard updated: 2026-08-13Import ID: vals-emb-2026-08-16-68d5d1d47a97Retrieved 2026-08-16 |
| Finance Agent (v2)Overall | 53.756 % | 55.044 %Winner | 2accuracyHigher is betterCohort: vals-finance-agent-v2:2:overallNo documented setup differenceWinner: GPT-5.6 LunaGPT-5.6 Sol: No further settings disclosed GPT-5.6 Luna: No further settings disclosed | Vals AIType: Independent evaluationLeaderboard updated: 2026-08-14Import ID: vals-fabv2-2026-08-16-8853da43085dRetrieved 2026-08-16 |
| GPQA DiamondOverall | 95.202 %Winner | 91.666 % | 1accuracyHigher is betterCohort: vals-gpqa:1:overallNo documented setup differenceWinner: GPT-5.6 SolGPT-5.6 Sol: No further settings disclosed GPT-5.6 Luna: No further settings disclosed | Vals AIType: Independent evaluationLeaderboard updated: 2026-08-12Import ID: vals-gpqa-2026-08-16-7f8363eaa2dbRetrieved 2026-08-16 |
| Harvey's Legal Agent BenchmarkOverall · Task fully resolved | 2.5 %Winner | 1.25 % | 1task resolution rateHigher is betterCohort: vals-legal-agent-benchmark:1:overallNo documented setup differenceWinner: GPT-5.6 SolGPT-5.6 Sol: No further settings disclosed GPT-5.6 Luna: No further settings disclosed | Vals AIType: Independent evaluationLeaderboard updated: 2026-08-14Import ID: vals-hlab-2026-08-16-bae90566df2fRetrieved 2026-08-16 |
| IOIOverall | 86.667 %Winner | 72.917 % | 1accuracyHigher is betterCohort: vals-ioi:1:overallNo documented setup differenceWinner: GPT-5.6 SolGPT-5.6 Sol: No further settings disclosed GPT-5.6 Luna: No further settings disclosed | Vals AIType: Independent evaluationLeaderboard updated: 2026-08-09Import ID: vals-ioi-2026-08-16-d9164ef483aaRetrieved 2026-08-16 |
| Legal Research BenchOverall · All-pass | 48.077 %Winner | 36.538 % | 1all-pass rateHigher is betterCohort: vals-legal-research:1:overallNo documented setup differenceWinner: GPT-5.6 SolGPT-5.6 Sol: No further settings disclosed GPT-5.6 Luna: No further settings disclosed | Vals AIType: Independent evaluationLeaderboard updated: 2026-08-14Import ID: vals-legal_research-2026-08-16-af296c00ecaaRetrieved 2026-08-16 |
| LegalBenchOverall | 86.965 %Winner | 84.034 % | 1accuracyHigher is betterCohort: vals-legal-bench:1:overallNo documented setup differenceWinner: GPT-5.6 SolGPT-5.6 Sol: No further settings disclosed GPT-5.6 Luna: No further settings disclosed | Vals AIType: Independent evaluationLeaderboard updated: 2026-08-12Import ID: vals-legal_bench-2026-08-16-d5b3b1b2b5c8Retrieved 2026-08-16 |
| MedCodeOverall | 43.974 %Winner | 42.391 % | 1accuracyHigher is betterCohort: vals-medcode:1:overallNo documented setup differenceWinner: GPT-5.6 SolGPT-5.6 Sol: No further settings disclosed GPT-5.6 Luna: No further settings disclosed | Vals AIType: Independent evaluationLeaderboard updated: 2026-08-12Import ID: vals-medcode-2026-08-16-524f7f474eacRetrieved 2026-08-16 |
| MedScribeOverall | 85.233 %Winner | 84.391 % | 1accuracyHigher is betterCohort: vals-medscribe:1:overallNo documented setup differenceWinner: GPT-5.6 SolGPT-5.6 Sol: No further settings disclosed GPT-5.6 Luna: No further settings disclosed | Vals AIType: Independent evaluationLeaderboard updated: 2026-08-12Import ID: vals-medscribe-2026-08-16-c385354a7e62Retrieved 2026-08-16 |
| MMLU-ProOverall | 89.1 %Winner | 86.036 % | 1accuracyHigher is betterCohort: vals-mmlu-pro:1:overallNo documented setup differenceWinner: GPT-5.6 SolGPT-5.6 Sol: No further settings disclosed GPT-5.6 Luna: No further settings disclosed | Vals AIType: Independent evaluationLeaderboard updated: 2026-08-12Import ID: vals-mmlu_pro-2026-08-16-e14d5bb3a34cRetrieved 2026-08-16 |
| MMMU-ProOverall | 88.844 %Winner | 85.029 % | 1accuracyHigher is betterCohort: vals-mmmu:1:overallNo documented setup differenceWinner: GPT-5.6 SolGPT-5.6 Sol: No further settings disclosed GPT-5.6 Luna: No further settings disclosed | Vals AIType: Independent evaluationLeaderboard updated: 2026-08-09Import ID: vals-mmmu-2026-08-16-37c9a8c7e21fRetrieved 2026-08-16 |
| MortgageTaxOverall | 67.289 % | 67.29 %Winner | 1accuracyHigher is betterCohort: vals-mortgage-tax:1:overallNo documented setup differenceWinner: GPT-5.6 LunaGPT-5.6 Sol: No further settings disclosed GPT-5.6 Luna: No further settings disclosed | Vals AIType: Independent evaluationLeaderboard updated: 2026-08-12Import ID: vals-mortgage_tax-2026-08-16-e78c985dbb1cRetrieved 2026-08-16 |
| ProgramBenchOverall | 1.5 %Winner | 0 % | 1accuracyHigher is betterCohort: vals-programbench:1:overallNo documented setup differenceWinner: GPT-5.6 SolGPT-5.6 Sol: No further settings disclosed GPT-5.6 Luna: No further settings disclosed | Vals AIType: Independent evaluationLeaderboard updated: 2026-08-13Import ID: vals-programbench-2026-08-16-08d9727662ddRetrieved 2026-08-16 |
| ProofBenchOverall | 83 %Winner | 60 % | 1.1accuracyHigher is betterCohort: vals-proof-bench:1.1:overallNo documented setup differenceWinner: GPT-5.6 SolGPT-5.6 Sol: No further settings disclosed GPT-5.6 Luna: No further settings disclosed | Vals AIType: Independent evaluationLeaderboard updated: 2026-08-14Import ID: vals-proof_bench-2026-08-16-14232db24de1Retrieved 2026-08-16 |
| Public Benefits Bench v1.1Overall | 66.509 %Winner | 61.164 % | 1.1accuracyHigher is betterCohort: vals-snap:1.1:overallNo documented setup differenceWinner: GPT-5.6 SolGPT-5.6 Sol: No further settings disclosed GPT-5.6 Luna: No further settings disclosed | Vals AIType: Independent evaluationLeaderboard updated: 2026-08-12Import ID: vals-public-benefits-bench-2026-08-16-7ce68123c502Retrieved 2026-08-16 |
| SAGEOverall | 52.563 %Winner | 44.22 % | 1accuracyHigher is betterCohort: vals-sage:1:overallNo documented setup differenceWinner: GPT-5.6 SolGPT-5.6 Sol: No further settings disclosed GPT-5.6 Luna: No further settings disclosed | Vals AIType: Independent evaluationLeaderboard updated: 2026-08-12Import ID: vals-sage-2026-08-16-a416dd25affbRetrieved 2026-08-16 |
| SkillsBenchOverall | 54.1 % | 60.447 %Winner | 1accuracyHigher is betterCohort: vals-skillsbench:1:overallNo documented setup differenceWinner: GPT-5.6 LunaGPT-5.6 Sol: Harness: OpenHands GPT-5.6 Luna: Harness: OpenHands | Vals AIType: Independent evaluationLeaderboard updated: 2026-08-13Import ID: vals-skillsbench-2026-08-16-4917a67268d2Retrieved 2026-08-16 |
| SWE-bench VerifiedOverall | 96.2 %Winner | 93 % | 1accuracyHigher is betterCohort: vals-swebench:1:overallNo documented setup differenceWinner: GPT-5.6 SolGPT-5.6 Sol: No further settings disclosed GPT-5.6 Luna: No further settings disclosed | Vals AIType: Independent evaluationLeaderboard updated: 2026-08-12Import ID: vals-swebench-2026-08-16-c133071b8167Retrieved 2026-08-16 |
| TaxEval v2Overall | 74.775 % | 76.166 %Winner | 2accuracyHigher is betterCohort: vals-tax-eval-v2:2:overallNo documented setup differenceWinner: GPT-5.6 LunaGPT-5.6 Sol: No further settings disclosed GPT-5.6 Luna: No further settings disclosed | Vals AIType: Independent evaluationLeaderboard updated: 2026-08-12Import ID: vals-tax_eval_v2-2026-08-16-5bbd495dac53Retrieved 2026-08-16 |
| Terminal-Bench 2.1Overall | 85.77 %Winner | 79.03 % | 2.1pass@1Higher is betterCohort: vals-terminal-bench-2-1-terminus2-2026-08-01No documented setup differenceWinner: GPT-5.6 SolGPT-5.6 Sol: Agent: Terminus 2, Harness: Terminus 2, Attempts: pass@1 GPT-5.6 Luna: Agent: Terminus 2, Harness: Terminus 2, Attempts: pass@1Constant Terminus 2 agent, 89 tasks, Daytona environments, and a shared time limit. | Vals AIType: Independent evaluationLeaderboard updated: 2026-08-01Import ID: curated-vals-ai-2026-08-02-db4549f6f7c5 / curated-vals-ai-2026-08-02-e60413c2fc2eRetrieved 2026-08-02 |
| Vals IndexOverall | 63.709 %Winner | 59.881 % | 2weighted index scoreHigher is betterCohort: vals-vals-index:2:overallNo documented setup differenceWinner: GPT-5.6 SolGPT-5.6 Sol: No further settings disclosed GPT-5.6 Luna: No further settings disclosed | Vals AIType: Independent evaluationLeaderboard updated: 2026-08-14Import ID: vals-vals_index-2026-08-16-ab641d89d6edRetrieved 2026-08-16 |
| Vals Multimodal IndexOverall | 72.64 %Winner | 69.058 % | 1.2weighted index scoreHigher is betterCohort: vals-vals-multimodal-index:1.2:overallNo documented setup differenceWinner: GPT-5.6 SolGPT-5.6 Sol: No further settings disclosed GPT-5.6 Luna: No further settings disclosed | Vals AIType: Independent evaluationLeaderboard updated: 2026-08-11Import ID: vals-vals_multimodal_index-2026-08-16-9f3ebb221408Retrieved 2026-08-16 |
| Vibe Code Bench v1.1Overall | 80.495 %Winner | 77.055 % | 1.1accuracyHigher is betterCohort: vals-vibe-code-bench:1.1:overallNo documented setup differenceWinner: GPT-5.6 SolGPT-5.6 Sol: Harness: OpenHands GPT-5.6 Luna: Harness: OpenHands | Vals AIType: Independent evaluationLeaderboard updated: 2026-08-13Import ID: vals-vibe-code-2026-08-16-a73c9770bcc4Retrieved 2026-08-16 |
| ARC-AGI-2OverallReasoning: low | 42.5 %Winner | 5.1 % | 2exact task accuracyHigher is betterCohort: arc-agi-2-gpt-5-6-reasoning-sweepNo documented setup differenceWinner: GPT-5.6 SolGPT-5.6 Sol: Reasoning: low, Attempts: two exact output guesses per task GPT-5.6 Luna: Reasoning: low, Attempts: two exact output guesses per taskThe same verified test with five reasoning levels per model. | ARC PrizeType: Official benchmark leaderboardLeaderboard updated: 2026-07-09Import ID: curated-arc-prize-2026-08-02-2c0171f05988 / curated-arc-prize-2026-08-02-3562cfe47bf2Retrieved 2026-08-02 |
| ARC-AGI-3RHAE overall score | 0.33 %Higher measured value | 0.18 % | ARC-AGI-3 2026 verifiedRHAE scoreHigher is betterCohort: arc-agi-3-semi-private-verified-official-harnessTest setup not documented as identicalNo direct winnerGPT-5.6 Sol: Reasoning: low, Agent: ARC Prize official harness, Harness: ARC Prize official harness GPT-5.6 Luna: Reasoning: max, Agent: ARC Prize official harness, Harness: ARC Prize official harnessOfficial ARC Prize harness on unseen interactive environments. Reasoning levels remain separate. | ARC PrizeType: Official benchmark leaderboardImport ID: curated-arc-prize-2026-08-06-691198a6be3b / curated-arc-prize-2026-08-06-7d499fffd2c4Retrieved 2026-08-06 |
| Arena Text, Style ControlBusiness, management and financeReasoning: xhigh | 1,482.723 arena pointsNo clear lead 95% confidence interval: ±11.356The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | 1,465.32 arena points 95% confidence interval: ±11.098The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | style-control-v1style-controlled Bradley-Terry ratingHigher is betterCohort: lmarena-text-style-control:2026-08-12:industry_business_and_management_and_financial_operationsNo documented setup differenceNo clear leadGPT-5.6 Sol: Snapshot: gpt-5.6-sol-xhigh, Reasoning: xhigh, Harness: Arena text, style control GPT-5.6 Luna: Snapshot: gpt-5.6-luna-xhigh, Reasoning: xhigh, Harness: Arena text, style controlGPT-5.6 Sol: Style-controlled Arena rating from 3,027 anonymous pairwise votes.GPT-5.6 Luna: Style-controlled Arena rating from 3,171 anonymous pairwise votes. | ArenaType: Official benchmark leaderboardLeaderboard updated: 2026-08-12Import ID: lmarena-eeedf9209373a7f9b324bfb839e7b02fedacd1e5-1611ed64f3f1Retrieved 2026-08-16 |
| BrowseCompOverall | 92.2 %Higher measured value Editorial selection from the vendor table, not a complete extract of the comparison cohort. | 83.3 % Editorial selection from the vendor table, not a complete extract of the comparison cohort. | 1,266 tasksaccuracyHigher is betterCohort: browsecomp-openai-gpt-5-6-tableTest setup not documented as identicalNo direct winnerGPT-5.6 Sol: Reasoning: ultra GPT-5.6 Luna: No further settings disclosedCross-vendor comparison table with browsing tools. Exact agent systems differ. | OpenAIType: Vendor-reportedLeaderboard updated: 2026-07-09Import ID: curated-openai-2026-08-02-aa55a6a6c756 / curated-openai-2026-08-02-65d8d2d5bbb4Retrieved 2026-08-02 |
| Code MigrationCLIReasoning: max | 47.221 %Winner | 36.067 % | 1accuracyHigher is betterCohort: vals-code-migration:1:cliNo documented setup differenceWinner: GPT-5.6 SolGPT-5.6 Sol: Reasoning: max, Output limit: 128,000 tokens GPT-5.6 Luna: Reasoning: max, Output limit: 128,000 tokens | Vals AIType: Independent evaluationLeaderboard updated: 2026-08-09Import ID: vals-code-migration-2026-08-11-3a2d5ce718a3Retrieved 2026-08-11 |
| CorpFin v2Exact PagesReasoning: max | 61.538 % | 63.52 %Winner | 2accuracyHigher is betterCohort: vals-corp-fin-v2:2:exact_pagesNo documented setup differenceWinner: GPT-5.6 LunaGPT-5.6 Sol: Reasoning: max, Output limit: 128,000 tokens GPT-5.6 Luna: Reasoning: max, Output limit: 128,000 tokens | Vals AIType: Independent evaluationLeaderboard updated: 2026-08-06Import ID: vals-corp_fin_v2-2026-08-11-d9e58d191cd9Retrieved 2026-08-11 |
| CyberBenchPatch | 83.051 %Winner | 79.661 % | 1accuracyHigher is betterCohort: vals-cyberbench:1:patchNo documented setup differenceWinner: GPT-5.6 SolGPT-5.6 Sol: No further settings disclosed GPT-5.6 Luna: No further settings disclosed | Vals AIType: Independent evaluationLeaderboard updated: 2026-08-03Import ID: vals-cyber-2026-08-11-1f20498a3dc1Retrieved 2026-08-11 |
| EMBCompsReasoning: max | 71.309 %Winner | 54.573 % | 1accuracyHigher is betterCohort: vals-emb:1:compsNo documented setup differenceWinner: GPT-5.6 SolGPT-5.6 Sol: Reasoning: max, Output limit: 128,000 tokens GPT-5.6 Luna: Reasoning: max, Output limit: 128,000 tokens | Vals AIType: Independent evaluationLeaderboard updated: 2026-08-06Import ID: vals-emb-2026-08-11-e3c855e236e4Retrieved 2026-08-11 |
| Finance Agent (v2)AdjustmentsReasoning: max | 49.233 % | 52.027 %Winner | 2accuracyHigher is betterCohort: vals-finance-agent-v2:2:adjustmentsNo documented setup differenceWinner: GPT-5.6 LunaGPT-5.6 Sol: Reasoning: max, Output limit: 128,000 tokens GPT-5.6 Luna: Reasoning: max, Output limit: 128,000 tokens | Vals AIType: Independent evaluationLeaderboard updated: 2026-08-06Import ID: vals-fabv2-2026-08-11-3e5c93a1857cRetrieved 2026-08-11 |
| GPQA DiamondFew-Shot CoTReasoning: max | 94.949 %Winner | 92.424 % | 1accuracyHigher is betterCohort: vals-gpqa:1:diamond_few_shot_cotNo documented setup differenceWinner: GPT-5.6 SolGPT-5.6 Sol: Reasoning: max, Output limit: 128,000 tokens GPT-5.6 Luna: Reasoning: max, Output limit: 128,000 tokens | Vals AIType: Independent evaluationLeaderboard updated: 2026-08-09Import ID: vals-gpqa-2026-08-11-d3325290a404Retrieved 2026-08-11 |
| Harvey's Legal Agent BenchmarkAntitrust Competition · Criteria passedReasoning: max | 78.623 % | 85.145 %Winner | 1criteria pass rateHigher is betterCohort: vals-legal-agent-benchmark:1:criteria_pass_rate__antitrust_competitionNo documented setup differenceWinner: GPT-5.6 LunaGPT-5.6 Sol: Reasoning: max, Output limit: 128,000 tokens GPT-5.6 Luna: Reasoning: max, Output limit: 128,000 tokens | Vals AIType: Independent evaluationLeaderboard updated: 2026-08-07Import ID: vals-hlab-2026-08-11-ea11b6e53414Retrieved 2026-08-11 |
| IOIIOI 2024Reasoning: max | 85 %Winner | 78 % | 1accuracyHigher is betterCohort: vals-ioi:1:ioi2024No documented setup differenceWinner: GPT-5.6 SolGPT-5.6 Sol: Reasoning: max, Output limit: 128,000 tokens GPT-5.6 Luna: Reasoning: max, Output limit: 128,000 tokens | Vals AIType: Independent evaluationLeaderboard updated: 2026-08-09Import ID: vals-ioi-2026-08-11-2dfe8b4b8b7bRetrieved 2026-08-11 |
| Legal Research BenchAdministrative / Regulatory · All-passReasoning: max | 60.606 %Winner | 48.485 % | 1all-pass rateHigher is betterCohort: vals-legal-research:1:administrative_regulatoryNo documented setup differenceWinner: GPT-5.6 SolGPT-5.6 Sol: Reasoning: max, Output limit: 128,000 tokens GPT-5.6 Luna: Reasoning: max, Output limit: 128,000 tokens | Vals AIType: Independent evaluationLeaderboard updated: 2026-08-06Import ID: vals-legal_research-2026-08-11-326cf7aaca58Retrieved 2026-08-11 |
| LegalBenchConclusion TasksReasoning: max | 90.492 %Winner | 88.864 % | 1accuracyHigher is betterCohort: vals-legal-bench:1:conclusion_tasksNo documented setup differenceWinner: GPT-5.6 SolGPT-5.6 Sol: Reasoning: max, Output limit: 128,000 tokens GPT-5.6 Luna: Reasoning: max, Output limit: 128,000 tokens | Vals AIType: Independent evaluationLeaderboard updated: 2026-08-09Import ID: vals-legal_bench-2026-08-11-836e5e44618eRetrieved 2026-08-11 |
| MMLU-ProBiologyReasoning: max | 94.561 %Winner | 93.305 % | 1accuracyHigher is betterCohort: vals-mmlu-pro:1:biologyNo documented setup differenceWinner: GPT-5.6 SolGPT-5.6 Sol: Reasoning: max, Output limit: 128,000 tokens GPT-5.6 Luna: Reasoning: max, Output limit: 128,000 tokens | Vals AIType: Independent evaluationLeaderboard updated: 2026-08-09Import ID: vals-mmlu_pro-2026-08-11-b8e53828d746Retrieved 2026-08-11 |
| MortgageTaxNumerical ExtractionReasoning: max | 75.119 % | 75.596 %Winner | 1accuracyHigher is betterCohort: vals-mortgage-tax:1:numerical_extractionNo documented setup differenceWinner: GPT-5.6 LunaGPT-5.6 Sol: Reasoning: max, Output limit: 128,000 tokens GPT-5.6 Luna: Reasoning: max, Output limit: 128,000 tokens | Vals AIType: Independent evaluationLeaderboard updated: 2026-08-09Import ID: vals-mortgage_tax-2026-08-11-5ea6eef3e482Retrieved 2026-08-11 |
| ProgramBenchAlmost ResolvedReasoning: max | 23 %Winner | 9 % | 1accuracyHigher is betterCohort: vals-programbench:1:almostNo documented setup differenceWinner: GPT-5.6 SolGPT-5.6 Sol: Reasoning: max, Output limit: 128,000 tokens GPT-5.6 Luna: Reasoning: max, Output limit: 128,000 tokens | Vals AIType: Independent evaluationLeaderboard updated: 2026-08-09Import ID: vals-programbench-2026-08-11-b6f8959fbdfeRetrieved 2026-08-11 |
| SAGEAutomataReasoning: max | 39.682 %Winner | 31.35 % | 1accuracyHigher is betterCohort: vals-sage:1:automataNo documented setup differenceWinner: GPT-5.6 SolGPT-5.6 Sol: Reasoning: max, Output limit: 30,000 tokens GPT-5.6 Luna: Reasoning: max, Output limit: 30,000 tokens | Vals AIType: Independent evaluationLeaderboard updated: 2026-08-09Import ID: vals-sage-2026-08-11-f1f79f6d8af3Retrieved 2026-08-11 |
| SkillsBenchNo SkillsReasoning: max | 43.312 % | 45.189 %Winner | 1accuracyHigher is betterCohort: vals-skillsbench:1:no_skillsNo documented setup differenceWinner: GPT-5.6 LunaGPT-5.6 Sol: Reasoning: max, Harness: OpenHands, Output limit: 128,000 tokens GPT-5.6 Luna: Reasoning: max, Harness: OpenHands, Output limit: 128,000 tokens | Vals AIType: Independent evaluationLeaderboard updated: 2026-08-07Import ID: vals-skillsbench-2026-08-11-351bec9d0e01Retrieved 2026-08-11 |
| SWE-bench Verified<15 min fixReasoning: max | 97.423 %Winner | 96.392 % | 1accuracyHigher is betterCohort: vals-swebench:1:<15 min fixNo documented setup differenceWinner: GPT-5.6 SolGPT-5.6 Sol: Reasoning: max, Output limit: 128,000 tokens GPT-5.6 Luna: Reasoning: max, Output limit: 128,000 tokens | Vals AIType: Independent evaluationLeaderboard updated: 2026-08-08Import ID: vals-swebench-2026-08-11-a6212cd857d8Retrieved 2026-08-11 |
| TaxEval v2CorrectnessReasoning: max | 65.004 % | 66.558 %Winner | 2accuracyHigher is betterCohort: vals-tax-eval-v2:2:correctnessNo documented setup differenceWinner: GPT-5.6 LunaGPT-5.6 Sol: Reasoning: max, Output limit: 128,000 tokens GPT-5.6 Luna: Reasoning: max, Output limit: 128,000 tokens | Vals AIType: Independent evaluationLeaderboard updated: 2026-08-09Import ID: vals-tax_eval_v2-2026-08-11-d05a40bf446fRetrieved 2026-08-11 |
| Terminal-Bench 2.1Overall | 85.768 %Winner | 79.026 % | 2.1accuracyHigher is betterCohort: vals-terminal-bench-2-1:2.1:overallNo documented setup differenceWinner: GPT-5.6 SolGPT-5.6 Sol: No further settings disclosed GPT-5.6 Luna: No further settings disclosed | Vals AIType: Independent evaluationLeaderboard updated: 2026-08-13Import ID: vals-terminal-bench-2-1-2026-08-16-b3f38c18bea4Retrieved 2026-08-16 |
| Vals IndexCorpFin v2Reasoning: max | 66.434 %Winner | 65.035 % | 1.2benchmark scoreHigher is betterCohort: vals-vals-index:1.2:corp_fin_v2No documented setup differenceWinner: GPT-5.6 SolGPT-5.6 Sol: Reasoning: max, Output limit: 128,000 tokens GPT-5.6 Luna: Reasoning: max, Output limit: 128,000 tokens | Vals AIType: Independent evaluationLeaderboard updated: 2026-08-09Import ID: vals-vals_index-2026-08-11-e79d08d59249Retrieved 2026-08-11 |
| Vals Multimodal IndexCorpFin v2Reasoning: max | 66.434 %Winner | 65.035 % | 1.2benchmark scoreHigher is betterCohort: vals-vals-multimodal-index:1.2:corp_fin_v2No documented setup differenceWinner: GPT-5.6 SolGPT-5.6 Sol: Reasoning: max, Output limit: 128,000 tokens GPT-5.6 Luna: Reasoning: max, Output limit: 128,000 tokens | Vals AIType: Independent evaluationLeaderboard updated: 2026-08-09Import ID: vals-vals_multimodal_index-2026-08-11-fa704862df19Retrieved 2026-08-11 |
| ARC-AGI-2OverallReasoning: max | 92.5 %Winner | 59.5 % | 2exact task accuracyHigher is betterCohort: arc-agi-2-gpt-5-6-reasoning-sweepNo documented setup differenceWinner: GPT-5.6 SolGPT-5.6 Sol: Reasoning: max, Attempts: two exact output guesses per task GPT-5.6 Luna: Reasoning: max, Attempts: two exact output guesses per taskThe same verified test with five reasoning levels per model. | ARC PrizeType: Official benchmark leaderboardLeaderboard updated: 2026-07-09Import ID: curated-arc-prize-2026-08-02-87b816b07dd2 / curated-arc-prize-2026-08-02-2b878d9a7edfRetrieved 2026-08-02 |
| ARC-AGI-3RHAE overall scoreReasoning: max | 7.78 %Winner | 0.18 % | ARC-AGI-3 2026 verifiedRHAE scoreHigher is betterCohort: arc-agi-3-semi-private-verified-official-harnessNo documented setup differenceWinner: GPT-5.6 SolGPT-5.6 Sol: Reasoning: max, Agent: ARC Prize official harness, Harness: ARC Prize official harness GPT-5.6 Luna: Reasoning: max, Agent: ARC Prize official harness, Harness: ARC Prize official harnessOfficial ARC Prize harness on unseen interactive environments. Reasoning levels remain separate. | ARC PrizeType: Official benchmark leaderboardImport ID: curated-arc-prize-2026-08-06-9ebb2edeedb6 / curated-arc-prize-2026-08-06-7d499fffd2c4Retrieved 2026-08-06 |
| Arena Text, Style ControlChineseReasoning: xhigh | 1,542.002 arena pointsWinner 95% confidence interval: ±19.125The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | 1,485.14 arena points 95% confidence interval: ±18.537The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result. | style-control-v1style-controlled Bradley-Terry ratingHigher is betterCohort: lmarena-text-style-control:2026-08-12:chineseNo documented setup differenceWinner: GPT-5.6 SolGPT-5.6 Sol: Snapshot: gpt-5.6-sol-xhigh, Reasoning: xhigh, Harness: Arena text, style control GPT-5.6 Luna: Snapshot: gpt-5.6-luna-xhigh, Reasoning: xhigh, Harness: Arena text, style controlGPT-5.6 Sol: Style-controlled Arena rating from 1,063 anonymous pairwise votes.GPT-5.6 Luna: Style-controlled Arena rating from 1,179 anonymous pairwise votes. | ArenaType: Official benchmark leaderboardLeaderboard updated: 2026-08-12Import ID: lmarena-eeedf9209373a7f9b324bfb839e7b02fedacd1e5-1611ed64f3f1Retrieved 2026-08-16 |
| Code MigrationCOBOLReasoning: max | 70 %Tie | 70 %Tie | 1accuracyHigher is betterCohort: vals-code-migration:1:cobolNo documented setup differenceTieGPT-5.6 Sol: Reasoning: max, Output limit: 128,000 tokens GPT-5.6 Luna: Reasoning: max, Output limit: 128,000 tokens | Vals AIType: Independent evaluationLeaderboard updated: 2026-08-09Import ID: vals-code-migration-2026-08-11-3a2d5ce718a3Retrieved 2026-08-11 |
| CorpFin v2Max Fitting ContextReasoning: max | 65.152 %Winner | 64.103 % | 2accuracyHigher is betterCohort: vals-corp-fin-v2:2:max_fitting_contextNo documented setup differenceWinner: GPT-5.6 SolGPT-5.6 Sol: Reasoning: max, Output limit: 128,000 tokens GPT-5.6 Luna: Reasoning: max, Output limit: 128,000 tokens | Vals AIType: Independent evaluationLeaderboard updated: 2026-08-06Import ID: vals-corp_fin_v2-2026-08-11-d9e58d191cd9Retrieved 2026-08-11 |
| CyberBenchPoC | 93.22 %Winner | 88.136 % | 1accuracyHigher is betterCohort: vals-cyberbench:1:pocNo documented setup differenceWinner: GPT-5.6 SolGPT-5.6 Sol: No further settings disclosed GPT-5.6 Luna: No further settings disclosed | Vals AIType: Independent evaluationLeaderboard updated: 2026-08-03Import ID: vals-cyber-2026-08-11-1f20498a3dc1Retrieved 2026-08-11 |
| EMBDataroomReasoning: max | 85.243 %Winner | 83.009 % | 1accuracyHigher is betterCohort: vals-emb:1:dataroomNo documented setup differenceWinner: GPT-5.6 SolGPT-5.6 Sol: Reasoning: max, Output limit: 128,000 tokens GPT-5.6 Luna: Reasoning: max, Output limit: 128,000 tokens | Vals AIType: Independent evaluationLeaderboard updated: 2026-08-06Import ID: vals-emb-2026-08-11-e3c855e236e4Retrieved 2026-08-11 |
| Finance Agent (v2)All-PassReasoning: max | 41.362 % | 43.285 %Winner | 2accuracyHigher is betterCohort: vals-finance-agent-v2:2:all_passNo documented setup differenceWinner: GPT-5.6 LunaGPT-5.6 Sol: Reasoning: max, Output limit: 128,000 tokens GPT-5.6 Luna: Reasoning: max, Output limit: 128,000 tokens | Vals AIType: Independent evaluationLeaderboard updated: 2026-08-06Import ID: vals-fabv2-2026-08-11-3e5c93a1857cRetrieved 2026-08-11 |
| GPQA DiamondZero-Shot CoTReasoning: max | 95.455 %Winner | 90.909 % | 1accuracyHigher is betterCohort: vals-gpqa:1:diamond_zero_shot_cotNo documented setup differenceWinner: GPT-5.6 SolGPT-5.6 Sol: Reasoning: max, Output limit: 128,000 tokens GPT-5.6 Luna: Reasoning: max, Output limit: 128,000 tokens | Vals AIType: Independent evaluationLeaderboard updated: 2026-08-09Import ID: vals-gpqa-2026-08-11-d3325290a404Retrieved 2026-08-11 |
| Harvey's Legal Agent BenchmarkAntitrust Competition · Task fully resolvedReasoning: max | 0 %Tie | 0 %Tie | 1task resolution rateHigher is betterCohort: vals-legal-agent-benchmark:1:antitrust_competitionNo documented setup differenceTieGPT-5.6 Sol: Reasoning: max, Output limit: 128,000 tokens GPT-5.6 Luna: Reasoning: max, Output limit: 128,000 tokens | Vals AIType: Independent evaluationLeaderboard updated: 2026-08-07Import ID: vals-hlab-2026-08-11-ea11b6e53414Retrieved 2026-08-11 |
The table shows 64 diversified result series from 216 shared results. This prevents one benchmark with many subtasks from crowding out every other test.
How to read this comparison
Winning one benchmark is not an overall verdict
Your workload, budget, and required context length matter most. A coding benchmark says little about visual understanding or agent performance.
Prices use official API rates per 1M tokens. Web subscriptions and cloud platform surcharges can differ.
Every result links to its measurement source and retrieval date. Labels distinguish vendor reports, official benchmark leaderboards, and independent evaluations. Disputed or archived results are excluded.
More matchups
Related LLM comparisons
Compare GPT-5.6 Sol and GPT-5.6 Luna with other leading models using the same data and benchmark logic.
View the complete LLM comparison