Model comparison
GPT-5 Nano vs Mistral Large
GPT-5 Nano is the stronger model overall, scoring 33.4 to 31.6 on the Noometry Index.
Last verified . 32 shared benchmarks.
Mistral AISummary
- They share 32 benchmarks with published results for both. GPT-5 Nano scores higher in 5 categories and Mistral Large in 4 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where GPT-5 Nano leads 29.1 to 17.1.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 81.1% for GPT-5 Nano and 8.5% for Mistral Large.
- GPT-5 Nano is cheaper at $0.05 / $0.40 per million input/output tokens, against $2 / $6 for Mistral Large.
- GPT-5 Nano accepts more context: 400K tokens versus 131K.
- Mistral Large has downloadable open weights; the other is API-only.
Side by side
| GPT-5 Nano | Mistral Large | |
|---|---|---|
| Provider | OpenAI | Mistral AI |
| Noometry Index | 33.4 | 31.6 |
| Released | 2025-08-07 | 2024-02-26 |
| Weights | Proprietary | Open |
| Context window | 400K | 131K |
| Max output | 128K | 16K |
| Input $ / M tokens | $0.05 | $2 |
| Output $ / M tokens | $0.40 | $6 |
| Results tracked | 48 | 51 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
GPT-5 Nano: 33.3 (#248), Mistral Large: 33.8 (#240)
| Benchmark | GPT-5 Nano | Mistral Large |
|---|---|---|
| LMArena Coding | 1351 | 1277 |
| ALE-Bench | 718.67 | 264.7 |
| SWE-bench Verified (bash only) | 34.8% | — |
| SciCode | — | 36.2% |
| WeirdML | 38.1% | — |
| BigCodeBench Instruct | — | 30% |
| LiveBench Coding | — | 47.1% |
| BigCodeBench Complete | — | 38.3% |
| HumanEval+ | — | 62.2% |
| MBPP+ | — | 59.5% |
Agentic & Tool Use Mistral Large leads
GPT-5 Nano: 25.6 (#99), Mistral Large: 28.4 (#83)
| Benchmark | GPT-5 Nano | Mistral Large |
|---|---|---|
| Berkeley Function Calling Leaderboard | 51.5% | 38.4% |
| Terminal-Bench | 21.8% | — |
Reasoning GPT-5 Nano leads
GPT-5 Nano: 16.4 (#291), Mistral Large: 15.4 (#305)
| Benchmark | GPT-5 Nano | Mistral Large |
|---|---|---|
| LMArena Hard Prompts | 1329 | 1257 |
| DTBench | 62.7% | 65.1% |
| LMCA | 7.9% | 16.7% |
| Epoch Capabilities Index | 139.39 | 128.52 |
| ForecastBench | 59.1 | 57.1 |
| ARC-AGI-2 | 2.6% | — |
| SimpleBench | — | 22.5% |
| Kagi LLM Benchmark | 62.2% | — |
| ARC-AGI-1 | 20.7% | — |
| CritPt | — | 0% |
| Chess Puzzles | 27% | — |
| LiveBench Reasoning | — | 43.5% |
| Mystery Game Puzzles | 9% | — |
| LiveBench Data Analysis | — | 50.1% |
| LiveBench | — | 48.4% |
Math GPT-5 Nano leads
GPT-5 Nano: 29.1 (#221), Mistral Large: 17.1 (#285)
| Benchmark | GPT-5 Nano | Mistral Large |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 81.1% | 8.5% |
| Omni-MATH | 54.6% | 28.1% |
| LMArena Math | 1318 | 1262 |
| MATH Level 5 | 95.2% | 50.3% |
| FrontierMath (Feb 2025 set) | 8.3% | 0.3% |
| FrontierMath (Tiers 1-3) | 20% | — |
| FrontierMath Tier 4 | 2.4% | — |
| ProofBench | 12% | — |
| LiveBench Math | — | 42.5% |
| FrontierMath Tier 4 (v1) | 2.1% | — |
Knowledge GPT-5 Nano leads
GPT-5 Nano: 35.8 (#166), Mistral Large: 30.0 (#224)
| Benchmark | GPT-5 Nano | Mistral Large |
|---|---|---|
| GPQA Diamond | 69.4% | 51.3% |
| MMLU-Pro | 77.8% | 59.9% |
| Vectara Hallucination Rate | 10.5% | 4.5% |
| GPQA (HELM) | 67.9% | 43.5% |
| LMArena Expert | 1321 | 1232 |
| SimpleQA Verified | 11.7% | — |
| Confabulations | — | 21.4% |
| MMLU | — | 80% |
Multimodal Not comparable
GPT-5 Nano: 30.7 (#102), Mistral Large: —
| Benchmark | GPT-5 Nano | Mistral Large |
|---|---|---|
| LMArena Vision | 1159 | — |
| VPCT | 37.2% | — |
Multilingual GPT-5 Nano leads
GPT-5 Nano: 45.5 (#167), Mistral Large: 40.1 (#214)
| Benchmark | GPT-5 Nano | Mistral Large |
|---|---|---|
| LMArena Non-English | 1313 | 1237 |
| LMArena Chinese | 1355 | 1240 |
| LMArena German | 1329 | 1254 |
| LMArena Korean | 1269 | 1202 |
| LMArena Russian | 1296 | 1257 |
| LMArena Spanish | 1360 | 1268 |
| LMArena French | — | 1324 |
| LMArena Japanese | — | 1187 |
Instruction Following GPT-5 Nano leads
GPT-5 Nano: 75.2 (#72), Mistral Large: 68.1 (#186)
| Benchmark | GPT-5 Nano | Mistral Large |
|---|---|---|
| IFEval | 93.2% | 87.7% |
| LMArena Instruction Following | 1306 | 1249 |
| LiveBench Instruction Following | — | 67.9% |
Long Context Mistral Large leads
GPT-5 Nano: 31.3 (#275), Mistral Large: 38.3 (#194)
| Benchmark | GPT-5 Nano | Mistral Large |
|---|---|---|
| LMArena Longer Query | 1313 | 1262 |
| Fiction.LiveBench | 44.4% | — |
Writing & Preference Mistral Large leads
GPT-5 Nano: 39.4 (#244), Mistral Large: 40.9 (#237)
| Benchmark | GPT-5 Nano | Mistral Large |
|---|---|---|
| LMArena Text | 1320 | 1266 |
| LMArena Creative Writing | 1250 | 1243 |
| EQ-Bench Creative Writing | 705 | 985 |
| WildBench | 80.6% | 80.1% |
| LMArena Multi-Turn | 1311 | 1260 |
| Short-Story Creative Writing | — | 69% |
| LiveBench Language | — | 39.4% |
Frequently asked questions
Is GPT-5 Nano better than Mistral Large?
GPT-5 Nano is the stronger model overall, scoring 33.4 to 31.6 on the Noometry Index.
Which is cheaper, GPT-5 Nano or Mistral Large?
GPT-5 Nano is cheaper. It lists at $0.05 per million input tokens and $0.40 per million output tokens; Mistral Large lists at $2 and $6.
Is GPT-5 Nano or Mistral Large better for coding?
They score almost the same on coding (33.3 vs 33.8); test both on your own repository before choosing.
Which has the bigger context window?
GPT-5 Nano does, with 400K tokens against 131K.
How many benchmarks do GPT-5 Nano and Mistral Large share?
32 benchmarks have published results for both models. GPT-5 Nano has 48 scored results on Noometry and Mistral Large has 51.