Model comparison
GPT-5 Nano vs Mistral 7B
GPT-5 Nano is the stronger model overall, scoring 33.5 to 23.0 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 7 categories and Mistral 7B in 1 category; 7 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where GPT-5 Nano leads 35.9 to 7.4.
- The biggest single-benchmark swing is MATH Level 5: 95.2% for GPT-5 Nano and 3.7% for Mistral 7B.
- GPT-5 Nano is cheaper at $0.05 / $0.40 per million input/output tokens, against $0.25 / $0.25 for Mistral 7B.
- GPT-5 Nano accepts more context: 400K tokens versus 8K.
- Mistral 7B has downloadable open weights; the other is API-only.
Side by side
| GPT-5 Nano | Mistral 7B | |
|---|---|---|
| Provider | OpenAI | Mistral AI |
| Noometry Index | 33.5 | 23.0 |
| Released | 2025-08-07 | 2023-09-27 |
| Weights | Proprietary | Open |
| Context window | 400K | 8K |
| Max output | 128K | 8K |
| Input $ / M tokens | $0.05 | $0.25 |
| Output $ / M tokens | $0.40 | $0.25 |
| Results tracked | 49 | 37 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-5 Nano leads
GPT-5 Nano: 33.6 (#254), Mistral 7B: 26.4 (#326)
| Benchmark | GPT-5 Nano | Mistral 7B |
|---|---|---|
| LMArena Coding | 1351 | 1082 |
| SWE-bench Verified (bash only) | 34.8% | — |
| WeirdML | 38.1% | — |
| BigCodeBench Instruct | — | 19.5% |
| BigCodeBench Complete | — | 27.3% |
| ALE-Bench | 718.67 | — |
| HumanEval+ | — | 36% |
| MBPP+ | — | 42.1% |
Agentic & Tool Use Not comparable
GPT-5 Nano: 25.8 (#106), Mistral 7B: —
| Benchmark | GPT-5 Nano | Mistral 7B |
|---|---|---|
| Terminal-Bench | 21.8% | — |
| Berkeley Function Calling Leaderboard | 51.5% | — |
Reasoning GPT-5 Nano leads
GPT-5 Nano: 16.3 (#306), Mistral 7B: 13.1 (#336)
| Benchmark | GPT-5 Nano | Mistral 7B |
|---|---|---|
| Chess Puzzles | 27% | 0% |
| LMArena Hard Prompts | 1328 | 1067 |
| DTBench | 62.7% | 42.5% |
| Epoch Capabilities Index | 139.38 | 112.21 |
| ARC-AGI-2 | 2.6% | — |
| Kagi LLM Benchmark | 62.2% | — |
| ARC-AGI-1 | 20.7% | — |
| Mystery Game Puzzles | 9% | — |
| LMCA | 7.9% | — |
| Adversarial NLI | — | 47.1% |
| BIG-Bench Hard | — | 56.1% |
| ForecastBench | 59.1 | — |
| HellaSwag | — | 81% |
| PIQA | — | 83% |
| WinoGrande | — | 75.3% |
Math GPT-5 Nano leads
GPT-5 Nano: 29.4 (#241), Mistral 7B: 8.1 (#325)
| Benchmark | GPT-5 Nano | Mistral 7B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 81.1% | 0.3% |
| LMArena Math | 1317 | 1085 |
| MATH Level 5 | 95.2% | 3.7% |
| FrontierMath (Tiers 1-3) | 20% | — |
| FrontierMath Tier 4 | 2.4% | — |
| ProofBench | 12% | — |
| Omni-MATH | 54.6% | — |
| FrontierMath (Feb 2025 set) | 8.3% | — |
| FrontierMath Tier 4 (v1) | 2.1% | — |
| GSM8K | — | 54.4% |
Knowledge GPT-5 Nano leads
GPT-5 Nano: 35.9 (#178), Mistral 7B: 7.4 (#311)
| Benchmark | GPT-5 Nano | Mistral 7B |
|---|---|---|
| GPQA Diamond | 69.4% | 15.2% |
| LMArena Expert | 1321 | 1036 |
| SimpleQA Verified | 11.7% | — |
| MMLU-Pro | 77.8% | — |
| Vectara Hallucination Rate | 10.5% | — |
| GPQA (HELM) | 67.9% | — |
| ARC (AI2) Challenge | — | 78.6% |
| BoolQ | — | 87.4% |
| MMLU | — | 62.5% |
| OpenBookQA | — | 79.8% |
| TriviaQA | — | 75.2% |
Multimodal Not comparable
GPT-5 Nano: 31.3 (#108), Mistral 7B: —
| Benchmark | GPT-5 Nano | Mistral 7B |
|---|---|---|
| LMArena Vision | 1159 | — |
| VPCT | 37.2% | — |
Multilingual GPT-5 Nano leads
GPT-5 Nano: 45.3 (#172), Mistral 7B: 25.8 (#283)
| Benchmark | GPT-5 Nano | Mistral 7B |
|---|---|---|
| LMArena Non-English | 1313 | 1012 |
| LMArena Chinese | 1356 | 1009 |
| LMArena German | 1327 | 987 |
| LMArena Japanese | 1226 | 878 |
| LMArena Russian | 1296 | 1018 |
| LMArena Spanish | 1360 | 1026 |
| LMArena French | — | 1037 |
| LMArena Korean | 1269 | — |
Instruction Following GPT-5 Nano leads
GPT-5 Nano: 75.0 (#79), Mistral 7B: 54.2 (#280)
| Benchmark | GPT-5 Nano | Mistral 7B |
|---|---|---|
| LMArena Instruction Following | 1306 | 1060 |
| IFEval | 93.2% | — |
Long Context Too close to call
GPT-5 Nano: 31.3 (#281), Mistral 7B: 32.2 (#271)
| Benchmark | GPT-5 Nano | Mistral 7B |
|---|---|---|
| LMArena Longer Query | 1312 | 1060 |
| Fiction.LiveBench | 44.4% | — |
Writing & Preference GPT-5 Nano leads
GPT-5 Nano: 39.1 (#249), Mistral 7B: 30.7 (#286)
| Benchmark | GPT-5 Nano | Mistral 7B |
|---|---|---|
| LMArena Text | 1320 | 1090 |
| LMArena Creative Writing | 1249 | 1068 |
| LMArena Multi-Turn | 1311 | 1062 |
| EQ-Bench Creative Writing | 705 | — |
| WildBench | 80.6% | — |
Frequently asked questions
Is GPT-5 Nano better than Mistral 7B?
GPT-5 Nano is the stronger model overall, scoring 33.5 to 23.0 on the Noometry Index.
Which is cheaper, GPT-5 Nano or Mistral 7B?
GPT-5 Nano is cheaper. It lists at $0.05 per million input tokens and $0.40 per million output tokens; Mistral 7B lists at $0.25 and $0.25.
Is GPT-5 Nano or Mistral 7B better for coding?
GPT-5 Nano scores higher on coding benchmarks: 33.6 versus 26.4 in the Noometry coding category.
Which has the bigger context window?
GPT-5 Nano does, with 400K tokens against 8K.
How many benchmarks do GPT-5 Nano and Mistral 7B share?
21 benchmarks have published results for both models. GPT-5 Nano has 49 scored results on Noometry and Mistral 7B has 37.