GPT-6 Luna
Not tested yet
Head-to-head comparison
GPT-6 Luna vs. MiMo-V2.5-Pro
Compare published benchmark results from matching versions and cohorts, API pricing, and technical specifications. Any documented test setup differences remain visible.
- shared result series
- 11
- distinct benchmarks
- 11
- latest retrieval
- 2026-09-23
Change model selection
Specifications
General specifications
Release date, availability, context window, architecture, and published parameter counts at a glance. Undisclosed details remain marked as unavailable.
| Attribute | GPT-6 Luna | MiMo-V2.5-Pro |
|---|---|---|
| Provider | OpenAI | Xiaomi |
| Released | Sep 22, 2026 | Apr 27, 2026 |
| Availability | Active | Open Source |
| Model type | Proprietary | Open Weights |
| Parameters | Not published | 1T, 42B active |
| Architecture | Not published | Mixture of Experts |
| Context window | 1,050,000 tokens | 1,000,000 tokens |
| Knowledge cutoff | May 18, 2026 | Not published |
| Technical sources | Model, Context | Model |
Pricing
API pricing compared
The table compares official standard API rates per 1M tokens, including published cache pricing. Batch, fast, priority, regional surcharges, tool calls, and cloud platform pricing are excluded.
| Price type | GPT-6 Luna | MiMo-V2.5-Pro |
|---|---|---|
| API input | $0.1 ≤272K / $0.2 >272K | $0.43 |
| API output | $0.5 ≤272K / $0.75 >272K | $0.87 |
| Cache read | $0.01 ≤272K / $0.02 >272K | $0. |
| Cache write (5 min.) | $0.13 ≤272K / $0.25 >272K | Not listed |
| Cache write (1 hr.) | Not listed | Not listed |
| Price verified | 09/22/2026 Source | 07/31/2026 Source |
GPT-6 LunaMiMo-V2.5-Pro
API inputUSD per 1M tokens, base tier
GPT-6 LunaLower price$0.1
MiMo-V2.5-Pro$0.435
API outputUSD per 1M tokens, base tier
GPT-6 LunaLower price$0.5
MiMo-V2.5-Pro$0.87
Cache readUSD per 1M tokens, base tier
GPT-6 Luna$0.01
MiMo-V2.5-ProLower price$0.004
Key to the marks:better valuebetter, but not conclusivetie
Pricing by provider
Direct developer pricing and provider endpoint tariffs routed through OpenRouter are listed separately. Prices are in USD per 1M tokens. Context-dependent direct tiers plus regional, Flex, Priority, and other OpenRouter tariffs remain individually identifiable.
| Model | Provider | Purchase route and tariff | Input per 1M tokens | Output per 1M tokens | Source |
|---|---|---|---|---|---|
| GPT-6 Luna | OpenAI | Direct from developerUp to 272,000 context tokens | $0.1 | Lowest listed price: $0.5 | Source09/22/2026 |
| OpenAI | Direct from developerAbove 272,000 context tokens | $0.2 | $0.75 | Source09/22/2026 | |
| Amazon Bedrock | Via OpenRouteramazon-bedrock/us-east-1 | $0.11 | $0.55 | Source09/23/2026 | |
| Azure | Via OpenRouterazure/eu | $0.11 | $0.55 | Source09/23/2026 | |
| Azure | Via OpenRouterazure/us | $0.11 | $0.55 | Source09/23/2026 | |
| OpenAI | Via OpenRouteropenai | Lowest listed price: $0.1 | Lowest listed price: $0.5 | Source09/23/2026 | |
| OpenAI | Via OpenRouteropenai/fast | $0.2 | $1 | Source09/23/2026 | |
| MiMo-V2.5-Pro | Xiaomi | Direct from developerStandard API | $0.435 | $0.87 | Source07/31/2026 |
| DeepInfra | Via OpenRouterdeepinfra/fp8 | $0.39 | $1.17 | Source09/23/2026 | |
| DigitalOcean | Via OpenRouterdigitalocean | $0.48 | $1.8 | Source09/23/2026 | |
| GMICloud | Via OpenRoutergmicloud/bf16 | Lowest listed price: $0.3045 | Lowest listed price: $0.609 | Source09/23/2026 | |
| Novita | Via OpenRouternovita | $0.4802 | $0.9605 | Source09/23/2026 | |
| StreamLake | Via OpenRouterstreamlake | $0.522 | $1.044 | Source09/23/2026 | |
| Xiaomi | Via OpenRouterxiaomi/fp8 | $0.435 | $0.87 | Source09/23/2026 |
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.
Capability profile from matched benchmarks
Each axis averages directly matched benchmark families. A value of 100 means the stronger value within this pair, not a universal quality score.
GPT-6 Luna
MiMo-V2.5-Pro
Coding: 100 / 46.2 (2 benchmark families)
Mathematics: 100 / 34.4 (1 benchmark family)
Finance: 100 / 81.9 (2 benchmark families)
Legal: 100 / 61.9 (2 benchmark families)
Agentic tasks: 100 / 78.5 (1 benchmark family)
Health: 100 / 86.3 (2 benchmark families)
Overall: 100 / 70.1 (1 benchmark family)
11 matched rows from 11 benchmark families were considered. The radar shows 7 of 7 comparable categories.
GPT-6 LunaMiMo-V2.5-Pro
Code MigrationOverall. Higher is better. No documented setup difference
GPT-6 LunaWinner42.554 %
MiMo-V2.5-Pro21.557 %
EMBOverall. Higher is better. No documented setup difference
GPT-6 LunaWinner68.515 %
MiMo-V2.5-Pro55.228 %
Finance Agent (v2)Overall. Higher is better. No documented setup difference
GPT-6 LunaWinner49.873 %
MiMo-V2.5-Pro41.502 %
Harvey's Legal Agent BenchmarkOverall · Task fully resolved. Higher is better. No documented setup difference
GPT-6 LunaWinner2.917 %
MiMo-V2.5-Pro2.083 %
Legal Research BenchOverall · All-pass. Higher is better. No documented setup difference
GPT-6 LunaWinner30.288 %
MiMo-V2.5-Pro15.865 %
MedCodeOverall. Higher is better. No documented setup difference
GPT-6 LunaWinner44.685 %
MiMo-V2.5-Pro32.484 %
MedScribeOverall. Higher is better. No documented setup difference
GPT-6 Luna83.71 %
MiMo-V2.5-ProWinner83.73 %
ProofBenchOverall. Higher is better. No documented setup difference
GPT-6 LunaWinner64 %
MiMo-V2.5-Pro22 %
Terminal-Bench 2.1Overall. Higher is better. No documented setup difference
GPT-6 LunaWinner73.034 %
MiMo-V2.5-Pro57.303 %
Vals IndexOverall. Higher is better. No documented setup difference
GPT-6 LunaWinner58.45 %
MiMo-V2.5-Pro40.974 %
Vibe Code Bench v1.1Overall. Higher is better. No documented setup difference
GPT-6 LunaWinner81.649 %
MiMo-V2.5-Pro34.113 %
Key to the marks:better valuebetter, but not conclusivetie
| Benchmark and task | GPT-6 Luna | MiMo-V2.5-Pro | Source |
|---|---|---|---|
Code MigrationOverallTest detailsNo documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is better | Winner42.554 % | 21.557 % | Vals AISource detailsData as of: 09/22/2026 |
EMBOverallTest detailsNo documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is better | Winner68.515 % | 55.228 % | Vals AISource detailsData as of: 09/22/2026 |
Finance Agent (v2)OverallTest detailsNo documented difference in the test setupVersion: 2Metric: accuracyScoring: Higher is better | Winner49.873 % | 41.502 % | Vals AISource detailsData as of: 09/22/2026 |
Harvey's Legal Agent BenchmarkOverall · Task fully resolvedTest detailsNo documented difference in the test setupVersion: 1Metric: task resolution rateScoring: Higher is better | Winner2.917 % | 2.083 % | Vals AISource detailsData as of: 09/22/2026 |
Legal Research BenchOverall · All-passTest detailsNo documented difference in the test setupVersion: 1Metric: all-pass rateScoring: Higher is better | Winner30.288 % | 15.865 % | Vals AISource detailsData as of: 09/22/2026 |
MedCodeOverallTest detailsNo documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is better | Winner44.685 % | 32.484 % | Vals AISource detailsData as of: 09/22/2026 |
MedScribeOverallTest detailsNo documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is better | 83.71 % | Winner83.73 % | Vals AISource detailsData as of: 09/22/2026 |
ProofBenchOverallTest detailsNo documented difference in the test setupVersion: 1.1Metric: accuracyScoring: Higher is better | Winner64 % | 22 % | Vals AISource detailsData as of: 09/22/2026 |
Terminal-Bench 2.1OverallTest detailsNo documented difference in the test setupVersion: 2.1Metric: accuracyScoring: Higher is better | Winner73.034 % | 57.303 % | Vals AISource detailsData as of: 09/22/2026 |
Vals IndexOverallTest detailsNo documented difference in the test setupVersion: 2Metric: weighted index scoreScoring: Higher is better | Winner58.45 % | 40.974 % | Vals AISource detailsData as of: 09/22/2026 |
Vibe Code Bench v1.1OverallTest detailsNo documented difference in the test setupVersion: 1.1Metric: accuracyScoring: Higher is betterSettings: Harness: OpenHands | Winner81.649 % | 34.113 % | Vals AISource detailsData as of: 09/22/2026 |
Key to the marks:better valuebetter, but not conclusivetie | |||
Our model tests
Our tests
Compare how the models respond to the same prompt. Each test shows the first attempt, with no subsequent fixes to the generated code. These results do not contribute to an overall score.
Pelican on a bicycle
A community classic for free-form SVG drawing.
MiMo-V2.5-Pro
API access was unavailable for this run. The model was not evaluated.
Reasoning (requested): high
First attempt
- Run date
- 7 Sept 2026
- API provider
- openrouter
- Requested API model
- xiaomi/mimo-v2.5-pro
- Reasoning setting
- high
- Pinned endpoint
- Xiaomi | xiaomi/mimo-v2.5-pro-20260422
- Temperature
- Provider default
- Token limit including reasoning
- 8,192 tokens
- Test protocol
- community-visual-tests-v1
- Technical checks
- Not run
Not yet visually reviewed. A successful recording does not confirm correct physics or full compliance with the prompt.
Prompt and test conditions
Generate an SVG of a pelican riding a bicycle
Token limit including reasoning: 8,192 tokens
Task origin (Simon Willison)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.
The standard price table uses direct developer rates. The provider comparison labels OpenRouter endpoints, regions, and special tariffs separately.
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-6 Luna and MiMo-V2.5-Pro with other leading models using the same data and benchmark logic.