Model comparison
GPT-6 Sol vs Mistral Large 3
GPT-6 Sol is the stronger model overall, scoring 61.8 to 39.1 on the Noometry Index. Mistral Large 3 costs 11× 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 7 categories and Mistral Large 3 in 2 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where GPT-6 Sol leads 74.0 to 15.2.
- The biggest single-benchmark swing is NYT Connections (extended): 90.1% for GPT-6 Sol and 7.5% for Mistral Large 3.
- Mistral Large 3 is cheaper at $0.25 / $0.75 per million input/output tokens, against $2 / $10 for GPT-6 Sol.
- GPT-6 Sol accepts more context: 1.05M tokens versus 262K.
- Mistral Large 3 has downloadable open weights; the other is API-only.
Side by side
| GPT-6 Sol | Mistral Large 3 | |
|---|---|---|
| Provider | OpenAI | Mistral AI |
| Noometry Index | 61.8 | 39.1 |
| Released | 2026-09-22 | 2025-12-02 |
| Weights | Proprietary | Open |
| Context window | 1.05M | 262K |
| Max output | 128K | 8K |
| Input $ / M tokens | $2 | $0.25 |
| Output $ / M tokens | $10 | $0.75 |
| Results tracked | 45 | 24 |
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 3: 34.4 (#237)
| Benchmark | GPT-6 Sol | Mistral Large 3 |
|---|---|---|
| LMArena WebDev | 1688 | 1230 |
| LMArena Coding | 1447 | 1448 |
| DeepSWE | 68.8% | — |
| FrontierCode | 49.3% | — |
| SciCode | 57.6% | — |
| ALE-Bench | 2,462 | — |
Agentic & Tool Use Not comparable
GPT-6 Sol: 37.2 (#36), Mistral Large 3: —
| Benchmark | GPT-6 Sol | Mistral Large 3 |
|---|---|---|
| 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 Large 3: 15.2 (#319)
| Benchmark | GPT-6 Sol | Mistral Large 3 |
|---|---|---|
| NYT Connections (extended) | 90.1% | 7.5% |
| LMArena Hard Prompts | 1418 | 1429 |
| ARC-AGI-2 | 89.6% | — |
| Kagi LLM Benchmark | — | 50.9% |
| ARC-AGI-1 | 95.5% | — |
| CritPt | 30.9% | — |
| Thematic Generalization | — | 23% |
| EBR-Bench | 53.3% | — |
| Mystery Game Puzzles | 56% | — |
| DTBench | 97.3% | — |
| LMCA | 59.1% | — |
| Epoch Capabilities Index | 162.72 | — |
Math GPT-6 Sol leads
GPT-6 Sol: 87.2 (#7), Mistral Large 3: 38.7 (#129)
| Benchmark | GPT-6 Sol | Mistral Large 3 |
|---|---|---|
| LMArena Math | 1402 | 1414 |
| FrontierMath (Tiers 1-3) | 89.8% | — |
| FrontierMath Tier 4 | 90% | — |
| OTIS Mock AIME 2024-2025 | 100% | — |
| ProofBench | 83% | — |
Knowledge GPT-6 Sol leads
GPT-6 Sol: 64.8 (#15), Mistral Large 3: 36.0 (#177)
| Benchmark | GPT-6 Sol | Mistral Large 3 |
|---|---|---|
| Vectara Hallucination Rate | 6.5% | 14.5% |
| LMArena Expert | 1439 | 1421 |
| GPQA Diamond | 94.3% | — |
| SimpleQA Verified | 60.7% | — |
Multimodal GPT-6 Sol leads
GPT-6 Sol: 47.6 (#10), Mistral Large 3: 38.2 (#66)
| Benchmark | GPT-6 Sol | Mistral Large 3 |
|---|---|---|
| LMArena Vision | 1245 | 1221 |
| Blueprint-Bench 2 | 36.9% | — |
| Furniture Assembly | 58.3% | — |
Multilingual Mistral Large 3 leads
GPT-6 Sol: 50.5 (#118), Mistral Large 3: 52.5 (#84)
| Benchmark | GPT-6 Sol | Mistral Large 3 |
|---|---|---|
| LMArena Non-English | 1385 | 1413 |
| LMArena Chinese | 1405 | 1447 |
| LMArena French | 1410 | 1455 |
| LMArena German | 1390 | 1437 |
| LMArena Japanese | 1385 | 1394 |
| LMArena Korean | 1341 | 1384 |
| LMArena Russian | 1401 | 1411 |
| LMArena Spanish | 1384 | 1440 |
Instruction Following Too close to call
GPT-6 Sol: 74.5 (#94), Mistral Large 3: 74.0 (#108)
| Benchmark | GPT-6 Sol | Mistral Large 3 |
|---|---|---|
| LMArena Instruction Following | 1412 | 1403 |
Long Context Too close to call
GPT-6 Sol: 43.1 (#108), Mistral Large 3: 43.1 (#105)
| Benchmark | GPT-6 Sol | Mistral Large 3 |
|---|---|---|
| LMArena Longer Query | 1411 | 1413 |
Writing & Preference GPT-6 Sol leads
GPT-6 Sol: 71.9 (#18), Mistral Large 3: 60.0 (#101)
| Benchmark | GPT-6 Sol | Mistral Large 3 |
|---|---|---|
| LMArena Text | 1395 | 1428 |
| LMArena Creative Writing | 1378 | 1386 |
| EQ-Bench Creative Writing | 2125 | 1412 |
| LMArena Multi-Turn | 1412 | 1429 |
Frequently asked questions
Is GPT-6 Sol better than Mistral Large 3?
GPT-6 Sol is the stronger model overall, scoring 61.8 to 39.1 on the Noometry Index. Mistral Large 3 costs 11× 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 Large 3?
Mistral Large 3 is cheaper. It lists at $0.25 per million input tokens and $0.75 per million output tokens; GPT-6 Sol lists at $2 and $10.
Is GPT-6 Sol or Mistral Large 3 better for coding?
GPT-6 Sol scores higher on coding benchmarks: 60.1 versus 34.4 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 Large 3 share?
22 benchmarks have published results for both models. GPT-6 Sol has 45 scored results on Noometry and Mistral Large 3 has 24.