Model comparison
GPT-6 Sol vs Mistral Large
GPT-6 Sol is the stronger model overall, scoring 61.8 to 31.9 on the Noometry Index.
Last verified . 27 shared benchmarks.
Mistral AISummary
- They share 27 benchmarks with published results for both. GPT-6 Sol scores higher in 9 categories and Mistral Large in 0 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where GPT-6 Sol leads 87.2 to 18.2.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 100% for GPT-6 Sol and 8.5% for Mistral Large.
- Mistral Large is cheaper at $2 / $6 per million input/output tokens, against $2 / $10 for GPT-6 Sol.
- GPT-6 Sol accepts more context: 1.05M tokens versus 131K.
- Mistral Large has downloadable open weights; the other is API-only.
Side by side
| GPT-6 Sol | Mistral Large | |
|---|---|---|
| Provider | OpenAI | Mistral AI |
| Noometry Index | 61.8 | 31.9 |
| Released | 2026-09-22 | 2024-02-26 |
| Weights | Proprietary | Open |
| Context window | 1.05M | 131K |
| Max output | 128K | 16K |
| Input $ / M tokens | $2 | $2 |
| Output $ / M tokens | $10 | $6 |
| Results tracked | 45 | 51 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-6 Sol leads
GPT-6 Sol: 60.1 (#11), Mistral Large: 34.3 (#240)
| Benchmark | GPT-6 Sol | Mistral Large |
|---|---|---|
| SciCode | 57.6% | 36.2% |
| LMArena Coding | 1447 | 1277 |
| ALE-Bench | 2,462 | 264.7 |
| DeepSWE | 68.8% | — |
| FrontierCode | 49.3% | — |
| LMArena WebDev | 1688 | — |
| BigCodeBench Instruct | — | 30% |
| LiveBench Coding | — | 47.1% |
| BigCodeBench Complete | — | 38.3% |
| HumanEval+ | — | 62.2% |
| MBPP+ | — | 59.5% |
Agentic & Tool Use GPT-6 Sol leads
GPT-6 Sol: 37.2 (#36), Mistral Large: 28.6 (#89)
| Benchmark | GPT-6 Sol | Mistral Large |
|---|---|---|
| APEX-Agents | 54.3% | — |
| Berkeley Function Calling Leaderboard | — | 38.4% |
| GDP.pdf | 26.4% | — |
| Vending-Bench 2 | 14,428 | — |
Reasoning GPT-6 Sol leads
GPT-6 Sol: 74.0 (#9), Mistral Large: 15.8 (#310)
| Benchmark | GPT-6 Sol | Mistral Large |
|---|---|---|
| CritPt | 30.9% | 0% |
| LMArena Hard Prompts | 1418 | 1257 |
| DTBench | 97.3% | 65.1% |
| LMCA | 59.1% | 16.7% |
| Epoch Capabilities Index | 162.72 | 128.52 |
| ARC-AGI-2 | 89.6% | — |
| SimpleBench | — | 22.5% |
| NYT Connections (extended) | 90.1% | — |
| ARC-AGI-1 | 95.5% | — |
| EBR-Bench | 53.3% | — |
| LiveBench Reasoning | — | 43.5% |
| Mystery Game Puzzles | 56% | — |
| LiveBench Data Analysis | — | 50.1% |
| ForecastBench | — | 57.1 |
| LiveBench | — | 48.4% |
Math GPT-6 Sol leads
GPT-6 Sol: 87.2 (#7), Mistral Large: 18.2 (#291)
| Benchmark | GPT-6 Sol | Mistral Large |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 100% | 8.5% |
| LMArena Math | 1402 | 1262 |
| FrontierMath (Tiers 1-3) | 89.8% | — |
| FrontierMath Tier 4 | 90% | — |
| ProofBench | 83% | — |
| Omni-MATH | — | 28.1% |
| LiveBench Math | — | 42.5% |
| MATH Level 5 | — | 50.3% |
| FrontierMath (Feb 2025 set) | — | 0.3% |
Knowledge GPT-6 Sol leads
GPT-6 Sol: 64.8 (#15), Mistral Large: 30.1 (#230)
| Benchmark | GPT-6 Sol | Mistral Large |
|---|---|---|
| GPQA Diamond | 94.3% | 51.3% |
| Vectara Hallucination Rate | 6.5% | 4.5% |
| LMArena Expert | 1439 | 1232 |
| SimpleQA Verified | 60.7% | — |
| MMLU-Pro | — | 59.9% |
| Confabulations | — | 21.4% |
| GPQA (HELM) | — | 43.5% |
| MMLU | — | 80% |
Multimodal Not comparable
GPT-6 Sol: 47.6 (#10), Mistral Large: —
| Benchmark | GPT-6 Sol | Mistral Large |
|---|---|---|
| LMArena Vision | 1245 | — |
| Blueprint-Bench 2 | 36.9% | — |
| Furniture Assembly | 58.3% | — |
Multilingual GPT-6 Sol leads
GPT-6 Sol: 50.5 (#118), Mistral Large: 40.0 (#219)
| Benchmark | GPT-6 Sol | Mistral Large |
|---|---|---|
| LMArena Non-English | 1385 | 1237 |
| LMArena Chinese | 1405 | 1240 |
| LMArena French | 1410 | 1325 |
| LMArena German | 1390 | 1254 |
| LMArena Japanese | 1385 | 1188 |
| LMArena Korean | 1341 | 1202 |
| LMArena Russian | 1401 | 1257 |
| LMArena Spanish | 1384 | 1268 |
Instruction Following GPT-6 Sol leads
GPT-6 Sol: 74.5 (#94), Mistral Large: 67.9 (#191)
| Benchmark | GPT-6 Sol | Mistral Large |
|---|---|---|
| LMArena Instruction Following | 1412 | 1249 |
| LiveBench Instruction Following | — | 67.9% |
| IFEval | — | 87.7% |
Long Context GPT-6 Sol leads
GPT-6 Sol: 43.1 (#108), Mistral Large: 38.3 (#199)
| Benchmark | GPT-6 Sol | Mistral Large |
|---|---|---|
| LMArena Longer Query | 1411 | 1261 |
Writing & Preference GPT-6 Sol leads
GPT-6 Sol: 71.9 (#18), Mistral Large: 40.7 (#242)
| Benchmark | GPT-6 Sol | Mistral Large |
|---|---|---|
| LMArena Text | 1395 | 1266 |
| LMArena Creative Writing | 1378 | 1243 |
| EQ-Bench Creative Writing | 2125 | 985 |
| LMArena Multi-Turn | 1412 | 1260 |
| Short-Story Creative Writing | — | 69% |
| WildBench | — | 80.1% |
| LiveBench Language | — | 39.4% |
Frequently asked questions
Is GPT-6 Sol better than Mistral Large?
GPT-6 Sol is the stronger model overall, scoring 61.8 to 31.9 on the Noometry Index.
Which is cheaper, GPT-6 Sol or Mistral Large?
Mistral Large is cheaper. It lists at $2 per million input tokens and $6 per million output tokens; GPT-6 Sol lists at $2 and $10.
Is GPT-6 Sol or Mistral Large better for coding?
GPT-6 Sol scores higher on coding benchmarks: 60.1 versus 34.3 in the Noometry coding category.
Which has the bigger context window?
GPT-6 Sol does, with 1.05M tokens against 131K.
How many benchmarks do GPT-6 Sol and Mistral Large share?
27 benchmarks have published results for both models. GPT-6 Sol has 45 scored results on Noometry and Mistral Large has 51.