Model comparison
GPT-5 Nano vs Mistral Small
GPT-5 Nano and Mistral Small score almost the same on the Noometry Index (33.5 vs 33.4), so choose on price, context window or the category you care about most.
Last verified . 26 shared benchmarks.
Mistral AISummary
- They share 26 benchmarks with published results for both. GPT-5 Nano scores higher in 3 categories and Mistral Small in 7 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Mistral Small leads 52.5 to 39.1.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 81.1% for GPT-5 Nano and 5.8% for Mistral Small.
- GPT-5 Nano is cheaper at $0.05 / $0.40 per million input/output tokens, against $0.15 / $0.60 for Mistral Small.
- GPT-5 Nano accepts more context: 400K tokens versus 262K.
- Mistral Small has downloadable open weights; the other is API-only.
Side by side
| GPT-5 Nano | Mistral Small | |
|---|---|---|
| Provider | OpenAI | Mistral AI |
| Noometry Index | 33.5 | 33.4 |
| Released | 2025-08-07 | 2024-02-26 |
| Weights | Proprietary | Open |
| Context window | 400K | 262K |
| Max output | 128K | 256K |
| Input $ / M tokens | $0.05 | $0.15 |
| Output $ / M tokens | $0.40 | $0.60 |
| Results tracked | 49 | 39 |
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 Small: 34.0 (#247)
| Benchmark | GPT-5 Nano | Mistral Small |
|---|---|---|
| LMArena Coding | 1351 | 1362 |
| ALE-Bench | 718.67 | 497.62 |
| SWE-bench Verified (bash only) | 34.8% | — |
| SciCode | — | 26.5% |
| WeirdML | 38.1% | — |
| BigCodeBench Instruct | — | 36.1% |
| LiveBench Coding | — | 36.2% |
| BigCodeBench Complete | — | 46.6% |
Agentic & Tool Use Mistral Small leads
GPT-5 Nano: 25.8 (#106), Mistral Small: 28.1 (#93)
| Benchmark | GPT-5 Nano | Mistral Small |
|---|---|---|
| Berkeley Function Calling Leaderboard | 51.5% | 37.1% |
| Terminal-Bench | 21.8% | — |
Reasoning Mistral Small leads
GPT-5 Nano: 16.3 (#306), Mistral Small: 19.8 (#250)
| Benchmark | GPT-5 Nano | Mistral Small |
|---|---|---|
| Kagi LLM Benchmark | 62.2% | 37.8% |
| LMArena Hard Prompts | 1328 | 1335 |
| DTBench | 62.7% | 70.9% |
| LMCA | 7.9% | 20.6% |
| ARC-AGI-2 | 2.6% | — |
| ARC-AGI-1 | 20.7% | — |
| CritPt | — | 0% |
| Chess Puzzles | 27% | — |
| LiveBench Reasoning | — | 44.8% |
| Mystery Game Puzzles | 9% | — |
| LiveBench Data Analysis | — | 53.7% |
| Epoch Capabilities Index | 139.38 | — |
| ForecastBench | 59.1 | — |
| LiveBench | — | 44% |
Math GPT-5 Nano leads
GPT-5 Nano: 29.4 (#241), Mistral Small: 16.4 (#293)
| Benchmark | GPT-5 Nano | Mistral Small |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 81.1% | 5.8% |
| LMArena Math | 1317 | 1341 |
| MATH Level 5 | 95.2% | 46.8% |
| FrontierMath (Tiers 1-3) | 20% | — |
| FrontierMath Tier 4 | 2.4% | — |
| ProofBench | 12% | — |
| Omni-MATH | 54.6% | — |
| LiveBench Math | — | 39.9% |
| FrontierMath (Feb 2025 set) | 8.3% | — |
| FrontierMath Tier 4 (v1) | 2.1% | — |
Knowledge GPT-5 Nano leads
GPT-5 Nano: 35.9 (#178), Mistral Small: 31.0 (#222)
| Benchmark | GPT-5 Nano | Mistral Small |
|---|---|---|
| GPQA Diamond | 69.4% | 47.5% |
| Vectara Hallucination Rate | 10.5% | 5.1% |
| LMArena Expert | 1321 | 1291 |
| SimpleQA Verified | 11.7% | — |
| MMLU-Pro | 77.8% | — |
| GPQA (HELM) | 67.9% | — |
| MMLU | — | 68.7% |
Multimodal Mistral Small leads
GPT-5 Nano: 31.3 (#108), Mistral Small: 33.5 (#96)
| Benchmark | GPT-5 Nano | Mistral Small |
|---|---|---|
| LMArena Vision | 1159 | 1142 |
| VPCT | 37.2% | — |
Multilingual Too close to call
GPT-5 Nano: 45.3 (#172), Mistral Small: 45.5 (#169)
| Benchmark | GPT-5 Nano | Mistral Small |
|---|---|---|
| LMArena Non-English | 1313 | 1315 |
| LMArena Chinese | 1356 | 1340 |
| LMArena German | 1327 | 1340 |
| LMArena Japanese | 1226 | 1275 |
| LMArena Korean | 1269 | 1259 |
| LMArena Russian | 1296 | 1324 |
| LMArena Spanish | 1360 | 1346 |
| LMArena French | — | 1337 |
Instruction Following GPT-5 Nano leads
GPT-5 Nano: 75.0 (#79), Mistral Small: 66.4 (#209)
| Benchmark | GPT-5 Nano | Mistral Small |
|---|---|---|
| LMArena Instruction Following | 1306 | 1310 |
| LiveBench Instruction Following | — | 63.7% |
| IFEval | 93.2% | — |
Long Context Mistral Small leads
GPT-5 Nano: 31.3 (#281), Mistral Small: 40.4 (#156)
| Benchmark | GPT-5 Nano | Mistral Small |
|---|---|---|
| LMArena Longer Query | 1312 | 1327 |
| Fiction.LiveBench | 44.4% | — |
Writing & Preference Mistral Small leads
GPT-5 Nano: 39.1 (#249), Mistral Small: 52.5 (#171)
| Benchmark | GPT-5 Nano | Mistral Small |
|---|---|---|
| LMArena Text | 1320 | 1338 |
| LMArena Creative Writing | 1249 | 1305 |
| LMArena Multi-Turn | 1311 | 1344 |
| EQ-Bench Creative Writing | 705 | — |
| WildBench | 80.6% | — |
| LiveBench Language | — | 30.5% |
Frequently asked questions
Is GPT-5 Nano better than Mistral Small?
GPT-5 Nano and Mistral Small score almost the same on the Noometry Index (33.5 vs 33.4), so choose on price, context window or the category you care about most.
Which is cheaper, GPT-5 Nano or Mistral Small?
GPT-5 Nano is cheaper. It lists at $0.05 per million input tokens and $0.40 per million output tokens; Mistral Small lists at $0.15 and $0.60.
Is GPT-5 Nano or Mistral Small better for coding?
They score almost the same on coding (33.6 vs 34.0); test both on your own repository before choosing.
Which has the bigger context window?
GPT-5 Nano does, with 400K tokens against 262K.
How many benchmarks do GPT-5 Nano and Mistral Small share?
26 benchmarks have published results for both models. GPT-5 Nano has 49 scored results on Noometry and Mistral Small has 39.