Model comparison
GPT-5.4 nano vs Mistral Large
GPT-5.4 nano is the stronger model overall, scoring 41.9 to 31.9 on the Noometry Index.
Last verified . 28 shared benchmarks.
Mistral AISummary
- They share 28 benchmarks with published results for both. GPT-5.4 nano scores higher in 8 categories and Mistral Large in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where GPT-5.4 nano leads 40.9 to 18.2.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 87.8% for GPT-5.4 nano and 8.5% for Mistral Large.
- GPT-5.4 nano is cheaper at $0.20 / $1.25 per million input/output tokens, against $2 / $6 for Mistral Large.
- GPT-5.4 nano accepts more context: 400K tokens versus 131K.
- Mistral Large has downloadable open weights; the other is API-only.
Side by side
| GPT-5.4 nano | Mistral Large | |
|---|---|---|
| Provider | OpenAI | Mistral AI |
| Noometry Index | 41.9 | 31.9 |
| Released | 2026-03-17 | 2024-02-26 |
| Weights | Proprietary | Open |
| Context window | 400K | 131K |
| Max output | 128K | 16K |
| Input $ / M tokens | $0.20 | $2 |
| Output $ / M tokens | $1.25 | $6 |
| Results tracked | 40 | 51 |
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 Large: 34.3 (#240)
| Benchmark | GPT-5.4 nano | Mistral Large |
|---|---|---|
| SciCode | 46.9% | 36.2% |
| LMArena Coding | 1405 | 1277 |
| ALE-Bench | 1,005 | 264.7 |
| WeirdML | 49.2% | — |
| BigCodeBench Instruct | — | 30% |
| LiveBench Coding | — | 47.1% |
| BigCodeBench Complete | — | 38.3% |
| HumanEval+ | — | 62.2% |
| MBPP+ | — | 59.5% |
Agentic & Tool Use Not comparable
GPT-5.4 nano: —, Mistral Large: 28.6 (#89)
| Benchmark | GPT-5.4 nano | Mistral Large |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 38.4% |
Reasoning GPT-5.4 nano leads
GPT-5.4 nano: 23.7 (#173), Mistral Large: 15.8 (#310)
| Benchmark | GPT-5.4 nano | Mistral Large |
|---|---|---|
| CritPt | 9.3% | 0% |
| LMArena Hard Prompts | 1381 | 1257 |
| DTBench | 80.3% | 65.1% |
| LMCA | 36.9% | 16.7% |
| Epoch Capabilities Index | 145.81 | 128.52 |
| ForecastBench | 57.3 | 57.1 |
| ARC-AGI-2 | 5.7% | — |
| SimpleBench | — | 22.5% |
| Kagi LLM Benchmark | 39.7% | — |
| ARC-AGI-1 | 51.5% | — |
| Chess Puzzles | 30% | — |
| LiveBench Reasoning | — | 43.5% |
| Mystery Game Puzzles | 9% | — |
| LiveBench Data Analysis | — | 50.1% |
| LiveBench | — | 48.4% |
Math GPT-5.4 nano leads
GPT-5.4 nano: 40.9 (#88), Mistral Large: 18.2 (#291)
| Benchmark | GPT-5.4 nano | Mistral Large |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 87.8% | 8.5% |
| LMArena Math | 1406 | 1262 |
| FrontierMath (Feb 2025 set) | 25.9% | 0.3% |
| FrontierMath (Tiers 1-3) | 44.9% | — |
| FrontierMath Tier 4 | 12.2% | — |
| ProofBench | 5% | — |
| Omni-MATH | — | 28.1% |
| LiveBench Math | — | 42.5% |
| MATH Level 5 | — | 50.3% |
| FrontierMath Tier 4 (v1) | 6.3% | — |
Knowledge GPT-5.4 nano leads
GPT-5.4 nano: 41.9 (#103), Mistral Large: 30.1 (#230)
| Benchmark | GPT-5.4 nano | Mistral Large |
|---|---|---|
| GPQA Diamond | 78.5% | 51.3% |
| Vectara Hallucination Rate | 3.1% | 4.5% |
| LMArena Expert | 1396 | 1232 |
| SimpleQA Verified | 11.7% | — |
| MMLU-Pro | — | 59.9% |
| Confabulations | — | 21.4% |
| GPQA (HELM) | — | 43.5% |
| MMLU | — | 80% |
Multimodal Not comparable
GPT-5.4 nano: 36.7 (#78), Mistral Large: —
| Benchmark | GPT-5.4 nano | Mistral Large |
|---|---|---|
| LMArena Vision | 1196 | — |
Multilingual GPT-5.4 nano leads
GPT-5.4 nano: 48.6 (#140), Mistral Large: 40.0 (#219)
| Benchmark | GPT-5.4 nano | Mistral Large |
|---|---|---|
| LMArena Non-English | 1359 | 1237 |
| LMArena Chinese | 1392 | 1240 |
| LMArena French | 1396 | 1325 |
| LMArena German | 1367 | 1254 |
| LMArena Japanese | 1343 | 1188 |
| LMArena Korean | 1320 | 1202 |
| LMArena Russian | 1363 | 1257 |
| LMArena Spanish | 1371 | 1268 |
Instruction Following GPT-5.4 nano leads
GPT-5.4 nano: 71.9 (#144), Mistral Large: 67.9 (#191)
| Benchmark | GPT-5.4 nano | Mistral Large |
|---|---|---|
| LMArena Instruction Following | 1362 | 1249 |
| LiveBench Instruction Following | — | 67.9% |
| IFEval | — | 87.7% |
Long Context GPT-5.4 nano leads
GPT-5.4 nano: 41.6 (#137), Mistral Large: 38.3 (#199)
| Benchmark | GPT-5.4 nano | Mistral Large |
|---|---|---|
| LMArena Longer Query | 1366 | 1261 |
Writing & Preference GPT-5.4 nano leads
GPT-5.4 nano: 55.7 (#142), Mistral Large: 40.7 (#242)
| Benchmark | GPT-5.4 nano | Mistral Large |
|---|---|---|
| LMArena Text | 1372 | 1266 |
| LMArena Creative Writing | 1314 | 1243 |
| LMArena Multi-Turn | 1382 | 1260 |
| Short-Story Creative Writing | — | 69% |
| EQ-Bench Creative Writing | — | 985 |
| WildBench | — | 80.1% |
| LiveBench Language | — | 39.4% |
Frequently asked questions
Is GPT-5.4 nano better than Mistral Large?
GPT-5.4 nano is the stronger model overall, scoring 41.9 to 31.9 on the Noometry Index.
Which is cheaper, GPT-5.4 nano or Mistral Large?
GPT-5.4 nano is cheaper. It lists at $0.20 per million input tokens and $1.25 per million output tokens; Mistral Large lists at $2 and $6.
Is GPT-5.4 nano or Mistral Large better for coding?
GPT-5.4 nano scores higher on coding benchmarks: 43.6 versus 34.3 in the Noometry coding category.
Which has the bigger context window?
GPT-5.4 nano does, with 400K tokens against 131K.
How many benchmarks do GPT-5.4 nano and Mistral Large share?
28 benchmarks have published results for both models. GPT-5.4 nano has 40 scored results on Noometry and Mistral Large has 51.