Model comparison
GPT-6 Sol vs Mistral Medium
GPT-6 Sol is the stronger model overall, scoring 61.8 to 36.3 on the Noometry Index.
Last verified . 28 shared benchmarks.
Mistral AISummary
- They share 28 benchmarks with published results for both. GPT-6 Sol scores higher in 9 categories and Mistral Medium in 1 category; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where GPT-6 Sol leads 87.2 to 28.1.
- The biggest single-benchmark swing is ProofBench: 83% for GPT-6 Sol and 9% for Mistral Medium.
- Mistral Medium is cheaper at $1.50 / $7.50 per million input/output tokens, against $2 / $10 for GPT-6 Sol.
- GPT-6 Sol accepts more context: 1.05M tokens versus 262K.
- Mistral Medium has downloadable open weights; the other is API-only.
Side by side
| GPT-6 Sol | Mistral Medium | |
|---|---|---|
| Provider | OpenAI | Mistral AI |
| Noometry Index | 61.8 | 36.3 |
| Released | 2026-09-22 | 2023-12-11 |
| Weights | Proprietary | Open |
| Context window | 1.05M | 262K |
| Max output | 128K | 262K |
| Input $ / M tokens | $2 | $1.50 |
| Output $ / M tokens | $10 | $7.50 |
| Results tracked | 45 | 36 |
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 Medium: 34.2 (#243)
| Benchmark | GPT-6 Sol | Mistral Medium |
|---|---|---|
| FrontierCode | 49.3% | 8% |
| SciCode | 57.6% | 40.2% |
| LMArena Coding | 1447 | 1434 |
| ALE-Bench | 2,462 | 763.98 |
| DeepSWE | 68.8% | — |
| LMArena WebDev | 1688 | — |
| WeirdML | — | 43.7% |
Agentic & Tool Use GPT-6 Sol leads
GPT-6 Sol: 37.2 (#36), Mistral Medium: 28.3 (#90)
| Benchmark | GPT-6 Sol | Mistral Medium |
|---|---|---|
| APEX-Agents | 54.3% | — |
| Berkeley Function Calling Leaderboard | — | 37.7% |
| GDP.pdf | 26.4% | — |
| Vending-Bench 2 | 14,428 | — |
Reasoning GPT-6 Sol leads
GPT-6 Sol: 74.0 (#9), Mistral Medium: 24.0 (#167)
| Benchmark | GPT-6 Sol | Mistral Medium |
|---|---|---|
| CritPt | 30.9% | 0% |
| LMArena Hard Prompts | 1418 | 1426 |
| DTBench | 97.3% | 75.5% |
| LMCA | 59.1% | 26.1% |
| ARC-AGI-2 | 89.6% | — |
| Kagi LLM Benchmark | — | 50% |
| NYT Connections (extended) | 90.1% | — |
| ARC-AGI-1 | 95.5% | — |
| EBR-Bench | 53.3% | — |
| Mystery Game Puzzles | 56% | — |
| Surface Evolver Bench | — | 26.9% |
| Epoch Capabilities Index | 162.72 | — |
Math GPT-6 Sol leads
GPT-6 Sol: 87.2 (#7), Mistral Medium: 28.1 (#245)
| Benchmark | GPT-6 Sol | Mistral Medium |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 100% | 32.2% |
| ProofBench | 83% | 9% |
| LMArena Math | 1402 | 1408 |
| FrontierMath (Tiers 1-3) | 89.8% | — |
| FrontierMath Tier 4 | 90% | — |
| MATH Level 5 | — | 81.6% |
| FrontierMath (Feb 2025 set) | — | 0.3% |
Knowledge GPT-6 Sol leads
GPT-6 Sol: 64.8 (#15), Mistral Medium: 25.0 (#265)
| Benchmark | GPT-6 Sol | Mistral Medium |
|---|---|---|
| GPQA Diamond | 94.3% | 59.5% |
| Vectara Hallucination Rate | 6.5% | 22.7% |
| LMArena Expert | 1439 | 1408 |
| Humanity's Last Exam | — | 4.5% |
| SimpleQA Verified | 60.7% | — |
Multimodal GPT-6 Sol leads
GPT-6 Sol: 47.6 (#10), Mistral Medium: 35.3 (#88)
| Benchmark | GPT-6 Sol | Mistral Medium |
|---|---|---|
| LMArena Vision | 1245 | 1172 |
| Blueprint-Bench 2 | 36.9% | — |
| Furniture Assembly | 58.3% | — |
Multilingual Mistral Medium leads
GPT-6 Sol: 50.5 (#118), Mistral Medium: 52.1 (#91)
| Benchmark | GPT-6 Sol | Mistral Medium |
|---|---|---|
| LMArena Non-English | 1385 | 1408 |
| LMArena Chinese | 1405 | 1447 |
| LMArena French | 1410 | 1459 |
| LMArena German | 1390 | 1432 |
| LMArena Japanese | 1385 | 1378 |
| LMArena Korean | 1341 | 1380 |
| LMArena Russian | 1401 | 1411 |
| LMArena Spanish | 1384 | 1433 |
Instruction Following Too close to call
GPT-6 Sol: 74.5 (#94), Mistral Medium: 73.7 (#116)
| Benchmark | GPT-6 Sol | Mistral Medium |
|---|---|---|
| LMArena Instruction Following | 1412 | 1398 |
Long Context Too close to call
GPT-6 Sol: 43.1 (#108), Mistral Medium: 42.9 (#114)
| Benchmark | GPT-6 Sol | Mistral Medium |
|---|---|---|
| LMArena Longer Query | 1411 | 1406 |
Writing & Preference GPT-6 Sol leads
GPT-6 Sol: 71.9 (#18), Mistral Medium: 60.0 (#103)
| Benchmark | GPT-6 Sol | Mistral Medium |
|---|---|---|
| LMArena Text | 1395 | 1424 |
| LMArena Creative Writing | 1378 | 1391 |
| LMArena Multi-Turn | 1412 | 1418 |
| Short-Story Creative Writing | — | 77.3% |
| EQ-Bench Creative Writing | 2125 | — |
Frequently asked questions
Is GPT-6 Sol better than Mistral Medium?
GPT-6 Sol is the stronger model overall, scoring 61.8 to 36.3 on the Noometry Index.
Which is cheaper, GPT-6 Sol or Mistral Medium?
Mistral Medium is cheaper. It lists at $1.50 per million input tokens and $7.50 per million output tokens; GPT-6 Sol lists at $2 and $10.
Is GPT-6 Sol or Mistral Medium better for coding?
GPT-6 Sol scores higher on coding benchmarks: 60.1 versus 34.2 in the Noometry coding category.
Which has the bigger context window?
GPT-6 Sol does, with 1.05M tokens against 262K.
How many benchmarks do GPT-6 Sol and Mistral Medium share?
28 benchmarks have published results for both models. GPT-6 Sol has 45 scored results on Noometry and Mistral Medium has 36.