Model comparison
GPT-5.4 nano vs Mistral
GPT-5.4 nano is the stronger model overall, scoring 41.9 to 29.9 on the Noometry Index.
Last verified . 17 shared benchmarks.
Mistral AISummary
- They share 17 benchmarks with published results for both. GPT-5.4 nano scores higher in 8 categories and Mistral in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where GPT-5.4 nano leads 41.9 to 16.6.
Side by side
| GPT-5.4 nano | Mistral | |
|---|---|---|
| Provider | OpenAI | Mistral AI |
| Noometry Index | 41.9 | 29.9 |
| Released | 2026-03-17 | — |
| Weights | Proprietary | Proprietary |
| Context window | 400K | — |
| Max output | 128K | — |
| Input $ / M tokens | $0.20 | — |
| Output $ / M tokens | $1.25 | — |
| Results tracked | 40 | 22 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-5.4 nano leads
GPT-5.4 nano: 43.6 (#84), Mistral: 33.8 (#250)
| Benchmark | GPT-5.4 nano | Mistral |
|---|---|---|
| LMArena Coding | 1405 | 1162 |
| SciCode | 46.9% | — |
| WeirdML | 49.2% | — |
| ALE-Bench | 1,005 | — |
Reasoning GPT-5.4 nano leads
GPT-5.4 nano: 23.7 (#173), Mistral: 22.2 (#200)
| Benchmark | GPT-5.4 nano | Mistral |
|---|---|---|
| LMArena Hard Prompts | 1381 | 1149 |
| ARC-AGI-2 | 5.7% | — |
| Kagi LLM Benchmark | 39.7% | — |
| ARC-AGI-1 | 51.5% | — |
| CritPt | 9.3% | — |
| Chess Puzzles | 30% | — |
| Mystery Game Puzzles | 9% | — |
| DTBench | 80.3% | — |
| LMCA | 36.9% | — |
| Epoch Capabilities Index | 145.81 | — |
| ForecastBench | 57.3 | — |
Math GPT-5.4 nano leads
GPT-5.4 nano: 40.9 (#88), Mistral: 22.3 (#278)
| Benchmark | GPT-5.4 nano | Mistral |
|---|---|---|
| LMArena Math | 1406 | 1180 |
| FrontierMath (Tiers 1-3) | 44.9% | — |
| FrontierMath Tier 4 | 12.2% | — |
| OTIS Mock AIME 2024-2025 | 87.8% | — |
| ProofBench | 5% | — |
| Omni-MATH | — | 7.2% |
| FrontierMath (Feb 2025 set) | 25.9% | — |
| FrontierMath Tier 4 (v1) | 6.3% | — |
Knowledge GPT-5.4 nano leads
GPT-5.4 nano: 41.9 (#103), Mistral: 16.6 (#288)
| Benchmark | GPT-5.4 nano | Mistral |
|---|---|---|
| LMArena Expert | 1396 | 1125 |
| GPQA Diamond | 78.5% | — |
| SimpleQA Verified | 11.7% | — |
| MMLU-Pro | — | 27.7% |
| Vectara Hallucination Rate | 3.1% | — |
| GPQA (HELM) | — | 30.3% |
Multimodal Not comparable
GPT-5.4 nano: 36.7 (#78), Mistral: —
| Benchmark | GPT-5.4 nano | Mistral |
|---|---|---|
| LMArena Vision | 1196 | — |
Multilingual GPT-5.4 nano leads
GPT-5.4 nano: 48.6 (#140), Mistral: 32.8 (#254)
| Benchmark | GPT-5.4 nano | Mistral |
|---|---|---|
| LMArena Non-English | 1359 | 1129 |
| LMArena Chinese | 1392 | 1109 |
| LMArena French | 1396 | 1180 |
| LMArena German | 1367 | 1155 |
| LMArena Japanese | 1343 | 1013 |
| LMArena Korean | 1320 | 1032 |
| LMArena Russian | 1363 | 1168 |
| LMArena Spanish | 1371 | 1143 |
Instruction Following GPT-5.4 nano leads
GPT-5.4 nano: 71.9 (#144), Mistral: 52.6 (#288)
| Benchmark | GPT-5.4 nano | Mistral |
|---|---|---|
| LMArena Instruction Following | 1362 | 1152 |
| IFEval | — | 56.8% |
Long Context GPT-5.4 nano leads
GPT-5.4 nano: 41.6 (#137), Mistral: 35.0 (#245)
| Benchmark | GPT-5.4 nano | Mistral |
|---|---|---|
| LMArena Longer Query | 1366 | 1153 |
Writing & Preference GPT-5.4 nano leads
GPT-5.4 nano: 55.7 (#142), Mistral: 37.0 (#260)
| Benchmark | GPT-5.4 nano | Mistral |
|---|---|---|
| LMArena Text | 1372 | 1165 |
| LMArena Creative Writing | 1314 | 1158 |
| LMArena Multi-Turn | 1382 | 1147 |
| WildBench | — | 66% |
Frequently asked questions
Is GPT-5.4 nano better than Mistral?
GPT-5.4 nano is the stronger model overall, scoring 41.9 to 29.9 on the Noometry Index.
Is GPT-5.4 nano or Mistral better for coding?
GPT-5.4 nano scores higher on coding benchmarks: 43.6 versus 33.8 in the Noometry coding category.
How many benchmarks do GPT-5.4 nano and Mistral share?
17 benchmarks have published results for both models. GPT-5.4 nano has 40 scored results on Noometry and Mistral has 22.