Model comparison
GPT-5 Nano vs Mistral
GPT-5 Nano is the stronger model overall, scoring 33.5 to 29.9 on the Noometry Index.
Last verified . 21 shared benchmarks.
Mistral AISummary
- They share 21 benchmarks with published results for both. GPT-5 Nano scores higher in 5 categories and Mistral in 3 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in instruction following, where GPT-5 Nano leads 75.0 to 52.6.
- The biggest single-benchmark swing is MMLU-Pro: 77.8% for GPT-5 Nano and 27.7% for Mistral.
Side by side
| GPT-5 Nano | Mistral | |
|---|---|---|
| Provider | OpenAI | Mistral AI |
| Noometry Index | 33.5 | 29.9 |
| Released | 2025-08-07 | — |
| Weights | Proprietary | Proprietary |
| Context window | 400K | — |
| Max output | 128K | — |
| Input $ / M tokens | $0.05 | — |
| Output $ / M tokens | $0.40 | — |
| Results tracked | 49 | 22 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
GPT-5 Nano: 33.6 (#254), Mistral: 33.8 (#250)
| Benchmark | GPT-5 Nano | Mistral |
|---|---|---|
| LMArena Coding | 1351 | 1162 |
| SWE-bench Verified (bash only) | 34.8% | — |
| WeirdML | 38.1% | — |
| ALE-Bench | 718.67 | — |
Agentic & Tool Use Not comparable
GPT-5 Nano: 25.8 (#106), Mistral: —
| Benchmark | GPT-5 Nano | Mistral |
|---|---|---|
| Terminal-Bench | 21.8% | — |
| Berkeley Function Calling Leaderboard | 51.5% | — |
Reasoning Mistral leads
GPT-5 Nano: 16.3 (#306), Mistral: 22.2 (#200)
| Benchmark | GPT-5 Nano | Mistral |
|---|---|---|
| LMArena Hard Prompts | 1328 | 1149 |
| ARC-AGI-2 | 2.6% | — |
| Kagi LLM Benchmark | 62.2% | — |
| ARC-AGI-1 | 20.7% | — |
| Chess Puzzles | 27% | — |
| Mystery Game Puzzles | 9% | — |
| DTBench | 62.7% | — |
| LMCA | 7.9% | — |
| Epoch Capabilities Index | 139.38 | — |
| ForecastBench | 59.1 | — |
Math GPT-5 Nano leads
GPT-5 Nano: 29.4 (#241), Mistral: 22.3 (#278)
| Benchmark | GPT-5 Nano | Mistral |
|---|---|---|
| Omni-MATH | 54.6% | 7.2% |
| LMArena Math | 1317 | 1180 |
| FrontierMath (Tiers 1-3) | 20% | — |
| FrontierMath Tier 4 | 2.4% | — |
| OTIS Mock AIME 2024-2025 | 81.1% | — |
| ProofBench | 12% | — |
| MATH Level 5 | 95.2% | — |
| FrontierMath (Feb 2025 set) | 8.3% | — |
| FrontierMath Tier 4 (v1) | 2.1% | — |
Knowledge GPT-5 Nano leads
GPT-5 Nano: 35.9 (#178), Mistral: 16.6 (#288)
| Benchmark | GPT-5 Nano | Mistral |
|---|---|---|
| MMLU-Pro | 77.8% | 27.7% |
| GPQA (HELM) | 67.9% | 30.3% |
| LMArena Expert | 1321 | 1125 |
| GPQA Diamond | 69.4% | — |
| SimpleQA Verified | 11.7% | — |
| Vectara Hallucination Rate | 10.5% | — |
Multimodal Not comparable
GPT-5 Nano: 31.3 (#108), Mistral: —
| Benchmark | GPT-5 Nano | Mistral |
|---|---|---|
| LMArena Vision | 1159 | — |
| VPCT | 37.2% | — |
Multilingual GPT-5 Nano leads
GPT-5 Nano: 45.3 (#172), Mistral: 32.8 (#254)
| Benchmark | GPT-5 Nano | Mistral |
|---|---|---|
| LMArena Non-English | 1313 | 1129 |
| LMArena Chinese | 1356 | 1109 |
| LMArena German | 1327 | 1155 |
| LMArena Japanese | 1226 | 1013 |
| LMArena Korean | 1269 | 1032 |
| LMArena Russian | 1296 | 1168 |
| LMArena Spanish | 1360 | 1143 |
| LMArena French | — | 1180 |
Instruction Following GPT-5 Nano leads
GPT-5 Nano: 75.0 (#79), Mistral: 52.6 (#288)
| Benchmark | GPT-5 Nano | Mistral |
|---|---|---|
| IFEval | 93.2% | 56.8% |
| LMArena Instruction Following | 1306 | 1152 |
Long Context Mistral leads
GPT-5 Nano: 31.3 (#281), Mistral: 35.0 (#245)
| Benchmark | GPT-5 Nano | Mistral |
|---|---|---|
| LMArena Longer Query | 1312 | 1153 |
| Fiction.LiveBench | 44.4% | — |
Writing & Preference GPT-5 Nano leads
GPT-5 Nano: 39.1 (#249), Mistral: 37.0 (#260)
| Benchmark | GPT-5 Nano | Mistral |
|---|---|---|
| LMArena Text | 1320 | 1165 |
| LMArena Creative Writing | 1249 | 1158 |
| WildBench | 80.6% | 66% |
| LMArena Multi-Turn | 1311 | 1147 |
| EQ-Bench Creative Writing | 705 | — |
Frequently asked questions
Is GPT-5 Nano better than Mistral?
GPT-5 Nano is the stronger model overall, scoring 33.5 to 29.9 on the Noometry Index.
Is GPT-5 Nano or Mistral better for coding?
They score almost the same on coding (33.6 vs 33.8); test both on your own repository before choosing.
How many benchmarks do GPT-5 Nano and Mistral share?
21 benchmarks have published results for both models. GPT-5 Nano has 49 scored results on Noometry and Mistral has 22.