Model comparison
GPT-4 Turbo vs Mistral
GPT-4 Turbo and Mistral score almost the same on the Noometry Index (30.3 vs 29.4), so choose on price, context window or the category you care about most.
Last verified . 17 shared benchmarks.
Mistral AISummary
- They share 17 benchmarks with published results for both. GPT-4 Turbo scores higher in 6 categories and Mistral in 2 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in instruction following, where GPT-4 Turbo leads 66.0 to 52.9.
Side by side
| GPT-4 Turbo | Mistral | |
|---|---|---|
| Provider | OpenAI | Mistral AI |
| Noometry Index | 30.3 | 29.4 |
| Released | 2023-11-06 | — |
| Weights | Proprietary | Proprietary |
| Context window | 128K | — |
| Max output | 4K | — |
| Input $ / M tokens | $10 | — |
| Output $ / M tokens | $30 | — |
| Results tracked | 36 | 22 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
GPT-4 Turbo: 33.4 (#247), Mistral: 33.2 (#249)
| Benchmark | GPT-4 Turbo | Mistral |
|---|---|---|
| LMArena Coding | 1268 | 1162 |
| WeirdML | 18% | — |
| BigCodeBench Instruct | 48.2% | — |
| BigCodeBench Complete | 58.2% | — |
| HumanEval+ | 86.6% | — |
| MBPP+ | 73.3% | — |
Agentic & Tool Use Not comparable
GPT-4 Turbo: —, Mistral: —
| Benchmark | GPT-4 Turbo | Mistral |
|---|---|---|
| METR Time Horizons | 36.7% | — |
Reasoning Mistral leads
GPT-4 Turbo: 14.9 (#311), Mistral: 21.3 (#199)
| Benchmark | GPT-4 Turbo | Mistral |
|---|---|---|
| LMArena Hard Prompts | 1251 | 1149 |
| SimpleBench | 25.1% | — |
| Chess Puzzles | 6% | — |
| DTBench | 61.6% | — |
| LMCA | 9.8% | — |
| Epoch Capabilities Index | 127.25 | — |
| ForecastBench | 59.4 | — |
Math Mistral leads
GPT-4 Turbo: 8.6 (#316), Mistral: 20.5 (#275)
| Benchmark | GPT-4 Turbo | Mistral |
|---|---|---|
| LMArena Math | 1272 | 1180 |
| FrontierMath (Tiers 1-3) | 0.7% | — |
| OTIS Mock AIME 2024-2025 | 6.7% | — |
| Omni-MATH | — | 7.2% |
| MATH Level 5 | 46.7% | — |
Knowledge GPT-4 Turbo leads
GPT-4 Turbo: 24.3 (#263), Mistral: 16.3 (#283)
| Benchmark | GPT-4 Turbo | Mistral |
|---|---|---|
| LMArena Expert | 1223 | 1125 |
| GPQA Diamond | 46.6% | — |
| MMLU-Pro | — | 27.7% |
| Confabulations | 28.4% | — |
| GPQA (HELM) | — | 30.3% |
| MMLU | 81.3% | — |
Multimodal Not comparable
GPT-4 Turbo: 30.0 (#104), Mistral: —
| Benchmark | GPT-4 Turbo | Mistral |
|---|---|---|
| LMArena Vision | 1090 | — |
Multilingual GPT-4 Turbo leads
GPT-4 Turbo: 40.7 (#211), Mistral: 33.0 (#249)
| Benchmark | GPT-4 Turbo | Mistral |
|---|---|---|
| LMArena Non-English | 1245 | 1129 |
| LMArena Chinese | 1242 | 1109 |
| LMArena French | 1275 | 1179 |
| LMArena German | 1259 | 1155 |
| LMArena Japanese | 1194 | 1012 |
| LMArena Korean | 1187 | 1032 |
| LMArena Russian | 1259 | 1168 |
| LMArena Spanish | 1260 | 1143 |
Instruction Following GPT-4 Turbo leads
GPT-4 Turbo: 66.0 (#211), Mistral: 52.9 (#283)
| Benchmark | GPT-4 Turbo | Mistral |
|---|---|---|
| LMArena Instruction Following | 1250 | 1152 |
| IFEval | — | 56.8% |
Long Context GPT-4 Turbo leads
GPT-4 Turbo: 38.0 (#200), Mistral: 35.0 (#240)
| Benchmark | GPT-4 Turbo | Mistral |
|---|---|---|
| LMArena Longer Query | 1254 | 1154 |
Writing & Preference GPT-4 Turbo leads
GPT-4 Turbo: 47.9 (#201), Mistral: 37.2 (#255)
| Benchmark | GPT-4 Turbo | Mistral |
|---|---|---|
| LMArena Text | 1272 | 1165 |
| LMArena Creative Writing | 1269 | 1158 |
| LMArena Multi-Turn | 1267 | 1147 |
| WildBench | — | 66% |
Frequently asked questions
Is GPT-4 Turbo better than Mistral?
GPT-4 Turbo and Mistral score almost the same on the Noometry Index (30.3 vs 29.4), so choose on price, context window or the category you care about most.
Is GPT-4 Turbo or Mistral better for coding?
They score almost the same on coding (33.4 vs 33.2); test both on your own repository before choosing.
How many benchmarks do GPT-4 Turbo and Mistral share?
17 benchmarks have published results for both models. GPT-4 Turbo has 36 scored results on Noometry and Mistral has 22.