GPT-6.1 Terravs.Muse Spark 1.3
Which one is better?
Level in the overall index: the gap is too small for a clear winner. GPT-6.1 Terra is cheaper for input, Muse Spark 1.3 for output.
67
GPT-6.1 Terra
Rank 12 to 27
69
Muse Spark 1.3
Rank 13 to 18
91
GPT-6.1 Terra
fairly slow
198
Muse Spark 1.3
fast
$2
GPT-6.1 Terra
fairly expensive
$2
Muse Spark 1.3
fairly expensive
GPT-6.1 Terra
- Subscription
Subscriptions in Germany: n/a
- Via API
$1 input, $5 output per 1M tokens.
Muse Spark 1.3
- Subscription
No Meta subscription includes this model. Through other providers from ≈ €10.60 a month (Command Code GOAT, with limited credits). 5 plans in Germany.
- Via API
$1.25 input, $4.25 output per 1M tokens, unchanged since Sep 3, 2026.
Overall index with data through Oct 29, 2026 · Prices from Oct 29, 2026 · Speed: measured by Artificial Analysis · Subscriptions as of Oct 24, 2026 · Subscription prices incl. VAT
Where is the difference?
Values from 0 to 100 per task area. We only name a winner when the gap is large enough and there are enough tests.
GPT-6.1 Terra ahead: 2Muse Spark 1.3 ahead: 1level: 2too little data: 4of 9 areas
AreaGPT-6.1 TerraMuse Spark 1.30 to 100, higher is betterResult
Areas in the overall index
CodingGPT-6.1 Terra aheadGPT-6.1 Terra: 84Muse Spark 1.3: 65
ReasoningGPT-6.1 Terra aheadGPT-6.1 Terra: 88Muse Spark 1.3: 74
Mathematicsonly Muse Spark 1.3 has a scoreGPT-6.1 Terra: not enough dataMuse Spark 1.3: 51
Knowledgetoo little dataGPT-6.1 Terra: 80Muse Spark 1.3: 71
AgentslevelGPT-6.1 Terra: 57Muse Spark 1.3: 58
Generalonly Muse Spark 1.3 has a scoreGPT-6.1 Terra: not enough dataMuse Spark 1.3: 72
Multimodaltoo little dataGPT-6.1 Terra: 70Muse Spark 1.3: 71
Specialist fields
FinancelevelGPT-6.1 Terra: 45Muse Spark 1.3: 79
LegalMuse Spark 1.3 aheadGPT-6.1 Terra: 8Muse Spark 1.3: 65
Show 1 more areas that do not count toward the overall index
AreaGPT-6.1 TerraMuse Spark 1.30 to 100, higher is betterResult
Cybersecurityonly Muse Spark 1.3 has a scoreGPT-6.1 Terra: not enough dataMuse Spark 1.3: 79
See for yourself: same task, one attempt
The same prompt for both models. We show the latest attempt without fixes; it does not count toward the overall index.
Pelican on a bicycle
A community classic for free-form SVG drawing.
GPT-6.1 Terra
Not tested yet
Muse Spark 1.3
Reasoning (requested): high
Current attempt
- Run date
- Oct 2, 2026
- API provider
- openrouter
- Requested API model
- meta/muse-spark-1.3
- API model reported in response
- meta/muse-spark-1.3
- Reasoning setting
- high
- Pinned endpoint
- Meta | meta/muse-spark-1.3-20260902
- Temperature
- Provider default
- Token limit including reasoning
- 8,192 tokens
- Test protocol
- community-visual-tests-v1
- Technical checks
- Passed, not a quality rating
- Response time
- 87.9 s
Visually reviewed. This individual test does not establish overall model quality.
Earlier attempts (2)
- Oct 1, 2026Output withheld for safetyReasoning setting: high
- Sep 7, 2026API request failedReasoning setting: high
Prompt and test conditions
Generate an SVG of a pelican riding a bicycle
Token limit including reasoning: 8,192 tokens
Task origin (Simon Willison)SVG short test
There is no shared test round for this selection. Results from different rounds are not mixed.
All data side by side
The better value is bold. For the overall index only when the gap is clear.
| Metric | GPT-6.1 Terra | Muse Spark 1.3 |
|---|---|---|
| Intelligence | ||
| Overall index0 to 100, higher is better | 67 | 69 |
| Rank | Rank 12 to 27 of 95 | Rank 13 to 18 of 95 |
| Price per 1M tokens | ||
| Inputwhat you send | $1above 272,000 tokens: $2 | $1.25 |
| Outputwhat the model writes | $5above 272,000 tokens: $7.50 | $4.25 |
| Speed | ||
| Tokens per second | 91 | 198 |
| Technical | ||
| Context windowhow much text the model reads at once | 1.05 M tokens≈ 1,580 A4 pages | 1.05 M tokens≈ 1,570 A4 pages |
| Knowledge cutoff | Jun 1, 2026 | n/a |
| Released | Oct 26, 2026 | Sep 2, 2026 |
| Availability | Active | Active |
| Open weights | no | no |
- GPT-6.1 Terra, 12-hour cache write: The table's cache-write rate covers 30-minute retention. With 12-hour retention it is $2.50 per 1M tokens through 272,000 input tokens, $5 above. Source
- GPT-6.1 Terra, Long-context billing: Above 272,000 input tokens, the higher rates apply to the entire request. Input and cache rates double, while output costs 1.5 times the standard rate. Source
- GPT-6.1 Terra, Batch and Flex pricing: 50% off standard pricing Source
- GPT-6.1 Terra, Fast pricing: Fast mode costs twice the standard price Source
- GPT-6.1 Terra, Regional processing: 10% surcharge over standard processing Source
Prices without caching or batch discounts · Page count as a rule of thumb from Artificial Analysis
Shared benchmarks
Single results from the same benchmark version, task and metric. A value is bold only with the same test setup and a clear gap.
A: GPT-6.1 TerraB: Muse Spark 1.3
AA-BriefcaseOverall · higher is betterGPT-6.1 Terra: 1,401.68 eloMuse Spark 1.3: 1,581.34 eloArtificial AnalysisAs of 10/29/2026
AA-OmniscienceOverall · higher is betterGPT-6.1 Terra: 29.567 pointsMuse Spark 1.3: 22.4 pointsArtificial AnalysisAs of 10/29/2026
AA-Omniscience AccuracyOverall · higher is betterGPT-6.1 Terra: 47.6%Muse Spark 1.3: 38.0%Artificial AnalysisAs of 10/29/2026
AA-Omniscience Hallucination RateOverall · lower is betterGPT-6.1 Terra: 34.5%Muse Spark 1.3: 25.2%Artificial AnalysisAs of 10/29/2026
Artificial Analysis Intelligence IndexOverall · higher is betterGPT-6.1 Terra: 50.977 pointsMuse Spark 1.3: 36.417 pointsArtificial AnalysisAs of 10/29/2026
AutomationBench-AAOverall · higher is betterGPT-6.1 Terra: 60.2%Muse Spark 1.3: 57.9%Artificial AnalysisAs of 10/29/2026
CritPt v2Overall · higher is betterGPT-6.1 Terra: 28.0%Muse Spark 1.3: 24.9%Artificial AnalysisAs of 10/29/2026
CritPt v2 (Hard Subset)Overall · higher is betterGPT-6.1 Terra: 64.5%Muse Spark 1.3: 46.0%Artificial AnalysisAs of 10/29/2026
FrontierCodeOverall · higher is betterGPT-6.1 Terra: 42.3%Muse Spark 1.3: 23.1%Artificial AnalysisAs of 10/29/2026
FrontierCode 1.1 MainOverall · higher is betterGPT-6.1 Terra: 36.0%Muse Spark 1.3: 40.6%Artificial AnalysisAs of 10/29/2026
Show 54 more benchmarks
GDP.pdfOverall · higher is betterGPT-6.1 Terra: 28.6%Muse Spark 1.3: 26.6%Artificial AnalysisAs of 10/29/2026
GDPval-AAOverall · higher is betterGPT-6.1 Terra: 1,476.05 eloMuse Spark 1.3: 1,680.99 eloArtificial AnalysisAs of 10/29/2026
HLE-DiamondOverall · higher is betterGPT-6.1 Terra: 47.3%Muse Spark 1.3: 33.7%Artificial AnalysisAs of 10/29/2026
Legal Research BenchOverall · All-pass · higher is betterTest setup not documented as identicalGPT-6.1 Terra: 26%Muse Spark 1.3: 40.9%Vals AIAs of 10/26/2026
MMMU-ProOverall · higher is betterGPT-6.1 Terra: 83.8%Muse Spark 1.3: 82.0%Artificial AnalysisAs of 10/29/2026
Tax Agent BenchOverall · higher is betterTest setup not documented as identicalGPT-6.1 Terra: 15.2%Muse Spark 1.3: 36%Vals AIAs of 10/26/2026
Terminal-BenchOverall · higher is betterGPT-6.1 Terra: 55.6%Muse Spark 1.3: 33.3%Artificial AnalysisAs of 10/29/2026
Terminal-Bench 4.0Overall · higher is betterTest setup not documented as identicalGPT-6.1 Terra: 49.5%Muse Spark 1.3: 10.6%Vals AIAs of 10/26/2026
Terminal-Bench-ScienceOverall · higher is betterGPT-6.1 Terra: 57.6%Muse Spark 1.3: 11.0%Artificial AnalysisAs of 10/29/2026
Vibe Code Bench v1.1Overall · higher is betterTest setup not documented as identicalGPT-6.1 Terra: 84%Muse Spark 1.3: 82.9%Vals AIAs of 10/26/2026
AA-Omniscience AccuracyOverall · higher is betterGPT-6.1 Terra: 48.0%Muse Spark 1.3: 37.8%Artificial AnalysisAs of 10/29/2026
AA-Omniscience Hallucination RateOverall · lower is betterGPT-6.1 Terra: 36.8%Muse Spark 1.3: 22.5%Artificial AnalysisAs of 10/29/2026
CritPt v2Overall · higher is betterGPT-6.1 Terra: 26.6%Muse Spark 1.3: 26.0%Artificial AnalysisAs of 10/29/2026
FrontierCode 1.1 MainOverall · higher is betterGPT-6.1 Terra: 41.4%Muse Spark 1.3: 38.6%Artificial AnalysisAs of 10/29/2026
GDPval-AAOverall · higher is betterGPT-6.1 Terra: 1,415.29 eloMuse Spark 1.3: 1,633.73 eloArtificial AnalysisAs of 10/29/2026
Legal Research BenchOverall · All-pass · higher is betterTest setup not documented as identicalGPT-6.1 Terra: 26%Muse Spark 1.3: 55.3%Vals AIAs of 10/26/2026
Tax Agent BenchOverall · higher is betterTest setup not documented as identicalGPT-6.1 Terra: 15.2%Muse Spark 1.3: 42.4%Vals AIAs of 10/26/2026
Terminal-Bench 4.0Overall · higher is betterTest setup not documented as identicalGPT-6.1 Terra: 49.5%Muse Spark 1.3: 24.7%Vals AIAs of 10/26/2026
Vibe Code Bench v1.1Overall · higher is betterTest setup not documented as identicalGPT-6.1 Terra: 84%Muse Spark 1.3: 85.9%Vals AIAs of 10/26/2026
Legal Research BenchAdministrative / Regulatory · All-pass · higher is betterTest setup not documented as identicalGPT-6.1 Terra: 45.5%Muse Spark 1.3: 51.5%Vals AIAs of 10/26/2026
Tax Agent BenchControversy & Precedence Analysis · higher is betterTest setup not documented as identicalGPT-6.1 Terra: 5.9%Muse Spark 1.3: 14.7%Vals AIAs of 10/26/2026
Terminal-Bench 4.0Hardware · higher is betterTest setup not documented as identicalGPT-6.1 Terra: 26.7%Muse Spark 1.3: 0%Vals AIAs of 10/26/2026
Legal Research BenchAdministrative / Regulatory · All-pass · higher is betterTest setup not documented as identicalGPT-6.1 Terra: 45.5%Muse Spark 1.3: 60.6%Vals AIAs of 10/26/2026
Tax Agent BenchControversy & Precedence Analysis · higher is betterTest setup not documented as identicalGPT-6.1 Terra: 5.9%Muse Spark 1.3: 36.7%Vals AIAs of 10/26/2026
Terminal-Bench 4.0Hardware · higher is betterTest setup not documented as identicalGPT-6.1 Terra: 26.7%Muse Spark 1.3: 0%Vals AIAs of 10/26/2026
Legal Research BenchAdministrative / Regulatory · Weighted partial credit · higher is betterTest setup not documented as identicalGPT-6.1 Terra: 84.8%Muse Spark 1.3: 85.9%Vals AIAs of 10/26/2026
Tax Agent BenchControversy & Precedence Analysis · higher is betterTest setup not documented as identicalGPT-6.1 Terra: 42.5%Muse Spark 1.3: 60.9%Vals AIAs of 10/26/2026
Terminal-Bench 4.0Media · higher is betterTest setup not documented as identicalGPT-6.1 Terra: 58.3%Muse Spark 1.3: 0%Vals AIAs of 10/26/2026
Legal Research BenchAdministrative / Regulatory · Weighted partial credit · higher is betterTest setup not documented as identicalGPT-6.1 Terra: 84.8%Muse Spark 1.3: 86.8%Vals AIAs of 10/26/2026
Tax Agent BenchControversy & Precedence Analysis · higher is betterTest setup not documented as identicalGPT-6.1 Terra: 42.5%Muse Spark 1.3: 68.7%Vals AIAs of 10/26/2026
Terminal-Bench 4.0Media · higher is betterTest setup not documented as identicalGPT-6.1 Terra: 58.3%Muse Spark 1.3: 16.7%Vals AIAs of 10/26/2026
Legal Research BenchBusiness & Commercial · All-pass · higher is betterTest setup not documented as identicalGPT-6.1 Terra: 16.3%Muse Spark 1.3: 32.6%Vals AIAs of 10/26/2026
Tax Agent BenchCurrent & Temporal Analysis · higher is betterTest setup not documented as identicalGPT-6.1 Terra: 22.1%Muse Spark 1.3: 49.8%Vals AIAs of 10/26/2026
Terminal-Bench 4.0ML · higher is betterTest setup not documented as identicalGPT-6.1 Terra: 42.4%Muse Spark 1.3: 21.2%Vals AIAs of 10/26/2026
Legal Research BenchBusiness & Commercial · All-pass · higher is betterTest setup not documented as identicalGPT-6.1 Terra: 16.3%Muse Spark 1.3: 58.1%Vals AIAs of 10/26/2026
Tax Agent BenchCurrent & Temporal Analysis · higher is betterTest setup not documented as identicalGPT-6.1 Terra: 22.1%Muse Spark 1.3: 42.3%Vals AIAs of 10/26/2026
Terminal-Bench 4.0ML · higher is betterTest setup not documented as identicalGPT-6.1 Terra: 42.4%Muse Spark 1.3: 30.3%Vals AIAs of 10/26/2026
Legal Research BenchBusiness & Commercial · Weighted partial credit · higher is betterTest setup not documented as identicalGPT-6.1 Terra: 75.9%Muse Spark 1.3: 88.2%Vals AIAs of 10/26/2026
Tax Agent BenchCurrent & Temporal Analysis · higher is betterTest setup not documented as identicalGPT-6.1 Terra: 53.1%Muse Spark 1.3: 73.1%Vals AIAs of 10/26/2026
Terminal-Bench 4.0Operations · higher is betterTest setup not documented as identicalGPT-6.1 Terra: 40.7%Muse Spark 1.3: 7.4%Vals AIAs of 10/26/2026
Legal Research BenchBusiness & Commercial · Weighted partial credit · higher is betterTest setup not documented as identicalGPT-6.1 Terra: 75.9%Muse Spark 1.3: 88.7%Vals AIAs of 10/26/2026
Tax Agent BenchCurrent & Temporal Analysis · higher is betterTest setup not documented as identicalGPT-6.1 Terra: 53.1%Muse Spark 1.3: 69.6%Vals AIAs of 10/26/2026
Terminal-Bench 4.0Operations · higher is betterTest setup not documented as identicalGPT-6.1 Terra: 40.7%Muse Spark 1.3: 11.1%Vals AIAs of 10/26/2026
Legal Research BenchCivil Litigation · All-pass · higher is betterTest setup not documented as identicalGPT-6.1 Terra: 14.8%Muse Spark 1.3: 40.7%Vals AIAs of 10/26/2026
Tax Agent BenchFact-Pattern Analysis · higher is betterTest setup not documented as identicalGPT-6.1 Terra: 16.1%Muse Spark 1.3: 45.8%Vals AIAs of 10/26/2026
Terminal-Bench 4.0Science · higher is betterTest setup not documented as identicalGPT-6.1 Terra: 54.8%Muse Spark 1.3: 11.9%Vals AIAs of 10/26/2026
Legal Research BenchCivil Litigation · All-pass · higher is betterTest setup not documented as identicalGPT-6.1 Terra: 14.8%Muse Spark 1.3: 63%Vals AIAs of 10/26/2026
Tax Agent BenchFact-Pattern Analysis · higher is betterTest setup not documented as identicalGPT-6.1 Terra: 16.1%Muse Spark 1.3: 43.7%Vals AIAs of 10/26/2026
Terminal-Bench 4.0Science · higher is betterTest setup not documented as identicalGPT-6.1 Terra: 54.8%Muse Spark 1.3: 26.2%Vals AIAs of 10/26/2026
Legal Research BenchCivil Litigation · Weighted partial credit · higher is betterTest setup not documented as identicalGPT-6.1 Terra: 80.6%Muse Spark 1.3: 91.2%Vals AIAs of 10/26/2026
Tax Agent BenchFact-Pattern Analysis · higher is betterTest setup not documented as identicalGPT-6.1 Terra: 47.2%Muse Spark 1.3: 75.1%Vals AIAs of 10/26/2026
Terminal-Bench 4.0Security · higher is betterTest setup not documented as identicalGPT-6.1 Terra: 80%Muse Spark 1.3: 0%Vals AIAs of 10/26/2026
Legal Research BenchCivil Litigation · Weighted partial credit · higher is betterTest setup not documented as identicalGPT-6.1 Terra: 80.6%Muse Spark 1.3: 90.9%Vals AIAs of 10/26/2026
Tax Agent BenchFact-Pattern Analysis · higher is betterTest setup not documented as identicalGPT-6.1 Terra: 47.2%Muse Spark 1.3: 70.2%Vals AIAs of 10/26/2026
Compare another matchup
More matchups
Related LLM comparisons
Compare GPT-6.1 Terra and Muse Spark 1.3 with other leading models.