Model comparison
GPT-6 Sol vs Mistral Small 3.1
GPT-6 Sol is the stronger model overall, scoring 61.8 to 31.7 on the Noometry Index. Mistral Small 3.1 costs 10.0× less per token, which makes it the better buy when GPT-6 Sol's lead doesn't matter for your workload.
Last verified . 22 shared benchmarks.
Mistral AISummary
- They share 22 benchmarks with published results for both. GPT-6 Sol scores higher in 9 categories and Mistral Small 3.1 in 0 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where GPT-6 Sol leads 87.2 to 14.7.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 100% for GPT-6 Sol and 3.9% for Mistral Small 3.1.
- Mistral Small 3.1 is cheaper at $0.35 / $0.56 per million input/output tokens, against $2 / $10 for GPT-6 Sol.
- GPT-6 Sol accepts more context: 1.05M tokens versus 128K.
- Mistral Small 3.1 has downloadable open weights; the other is API-only.
Side by side
| GPT-6 Sol | Mistral Small 3.1 | |
|---|---|---|
| Provider | OpenAI | Mistral AI |
| Noometry Index | 61.8 | 31.7 |
| Released | 2026-09-22 | 2025-03-17 |
| Weights | Proprietary | Open |
| Context window | 1.05M | 128K |
| Max output | 128K | 102K |
| Input $ / M tokens | $2 | $0.35 |
| Output $ / M tokens | $10 | $0.56 |
| Results tracked | 45 | 28 |
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 Small 3.1: 38.3 (#179)
| Benchmark | GPT-6 Sol | Mistral Small 3.1 |
|---|---|---|
| LMArena Coding | 1447 | 1309 |
| DeepSWE | 68.8% | — |
| FrontierCode | 49.3% | — |
| LMArena WebDev | 1688 | — |
| SciCode | 57.6% | — |
| ALE-Bench | 2,462 | — |
Agentic & Tool Use Not comparable
GPT-6 Sol: 37.2 (#36), Mistral Small 3.1: —
| Benchmark | GPT-6 Sol | Mistral Small 3.1 |
|---|---|---|
| APEX-Agents | 54.3% | — |
| GDP.pdf | 26.4% | — |
| Vending-Bench 2 | 14,428 | — |
Reasoning GPT-6 Sol leads
GPT-6 Sol: 74.0 (#9), Mistral Small 3.1: 19.7 (#254)
| Benchmark | GPT-6 Sol | Mistral Small 3.1 |
|---|---|---|
| LMArena Hard Prompts | 1418 | 1278 |
| Epoch Capabilities Index | 162.72 | 127.48 |
| ARC-AGI-2 | 89.6% | — |
| NYT Connections (extended) | 90.1% | — |
| ARC-AGI-1 | 95.5% | — |
| CritPt | 30.9% | — |
| Chess Puzzles | — | 1% |
| EBR-Bench | 53.3% | — |
| Mystery Game Puzzles | 56% | — |
| DTBench | 97.3% | — |
| LMCA | 59.1% | — |
Math GPT-6 Sol leads
GPT-6 Sol: 87.2 (#7), Mistral Small 3.1: 14.7 (#301)
| Benchmark | GPT-6 Sol | Mistral Small 3.1 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 100% | 3.9% |
| LMArena Math | 1402 | 1262 |
| FrontierMath (Tiers 1-3) | 89.8% | — |
| FrontierMath Tier 4 | 90% | — |
| ProofBench | 83% | — |
| Omni-MATH | — | 24.8% |
Knowledge GPT-6 Sol leads
GPT-6 Sol: 64.8 (#15), Mistral Small 3.1: 22.6 (#271)
| Benchmark | GPT-6 Sol | Mistral Small 3.1 |
|---|---|---|
| GPQA Diamond | 94.3% | 41.9% |
| LMArena Expert | 1439 | 1257 |
| SimpleQA Verified | 60.7% | — |
| MMLU-Pro | — | 61% |
| Vectara Hallucination Rate | 6.5% | — |
| GPQA (HELM) | — | 39.2% |
Multimodal GPT-6 Sol leads
GPT-6 Sol: 47.6 (#10), Mistral Small 3.1: 33.2 (#99)
| Benchmark | GPT-6 Sol | Mistral Small 3.1 |
|---|---|---|
| LMArena Vision | 1245 | 1136 |
| Blueprint-Bench 2 | 36.9% | — |
| Furniture Assembly | 58.3% | — |
Multilingual GPT-6 Sol leads
GPT-6 Sol: 50.5 (#118), Mistral Small 3.1: 41.2 (#209)
| Benchmark | GPT-6 Sol | Mistral Small 3.1 |
|---|---|---|
| LMArena Non-English | 1385 | 1255 |
| LMArena Chinese | 1405 | 1253 |
| LMArena French | 1410 | 1273 |
| LMArena German | 1390 | 1266 |
| LMArena Japanese | 1385 | 1208 |
| LMArena Korean | 1341 | 1206 |
| LMArena Russian | 1401 | 1263 |
| LMArena Spanish | 1384 | 1283 |
Instruction Following GPT-6 Sol leads
GPT-6 Sol: 74.5 (#94), Mistral Small 3.1: 63.6 (#230)
| Benchmark | GPT-6 Sol | Mistral Small 3.1 |
|---|---|---|
| LMArena Instruction Following | 1412 | 1264 |
| IFEval | — | 75% |
Long Context GPT-6 Sol leads
GPT-6 Sol: 43.1 (#108), Mistral Small 3.1: 39.5 (#178)
| Benchmark | GPT-6 Sol | Mistral Small 3.1 |
|---|---|---|
| LMArena Longer Query | 1411 | 1299 |
Writing & Preference GPT-6 Sol leads
GPT-6 Sol: 71.9 (#18), Mistral Small 3.1: 37.0 (#259)
| Benchmark | GPT-6 Sol | Mistral Small 3.1 |
|---|---|---|
| LMArena Text | 1395 | 1277 |
| LMArena Creative Writing | 1378 | 1253 |
| EQ-Bench Creative Writing | 2125 | 761 |
| LMArena Multi-Turn | 1412 | 1270 |
| WildBench | — | 78.8% |
Frequently asked questions
Is GPT-6 Sol better than Mistral Small 3.1?
GPT-6 Sol is the stronger model overall, scoring 61.8 to 31.7 on the Noometry Index. Mistral Small 3.1 costs 10.0× less per token, which makes it the better buy when GPT-6 Sol's lead doesn't matter for your workload.
Which is cheaper, GPT-6 Sol or Mistral Small 3.1?
Mistral Small 3.1 is cheaper. It lists at $0.35 per million input tokens and $0.56 per million output tokens; GPT-6 Sol lists at $2 and $10.
Is GPT-6 Sol or Mistral Small 3.1 better for coding?
GPT-6 Sol scores higher on coding benchmarks: 60.1 versus 38.3 in the Noometry coding category.
Which has the bigger context window?
GPT-6 Sol does, with 1.05M tokens against 128K.
How many benchmarks do GPT-6 Sol and Mistral Small 3.1 share?
22 benchmarks have published results for both models. GPT-6 Sol has 45 scored results on Noometry and Mistral Small 3.1 has 28.