Model comparison
GPT-5.4 nano vs Mistral Medium
GPT-5.4 nano is the stronger model overall, scoring 41.9 to 36.3 on the Noometry Index.
Last verified . 30 shared benchmarks.
Mistral AISummary
- They share 30 benchmarks with published results for both. GPT-5.4 nano scores higher in 4 categories and Mistral Medium in 5 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where GPT-5.4 nano leads 41.9 to 25.0.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 87.8% for GPT-5.4 nano and 32.2% for Mistral Medium.
- GPT-5.4 nano is cheaper at $0.20 / $1.25 per million input/output tokens, against $1.50 / $7.50 for Mistral Medium.
- GPT-5.4 nano accepts more context: 400K tokens versus 262K.
- Mistral Medium has downloadable open weights; the other is API-only.
Side by side
| GPT-5.4 nano | Mistral Medium | |
|---|---|---|
| Provider | OpenAI | Mistral AI |
| Noometry Index | 41.9 | 36.3 |
| Released | 2026-03-17 | 2023-12-11 |
| Weights | Proprietary | Open |
| Context window | 400K | 262K |
| Max output | 128K | 262K |
| Input $ / M tokens | $0.20 | $1.50 |
| Output $ / M tokens | $1.25 | $7.50 |
| Results tracked | 40 | 36 |
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 Medium: 34.2 (#243)
| Benchmark | GPT-5.4 nano | Mistral Medium |
|---|---|---|
| SciCode | 46.9% | 40.2% |
| WeirdML | 49.2% | 43.7% |
| LMArena Coding | 1405 | 1434 |
| ALE-Bench | 1,005 | 763.98 |
| FrontierCode | — | 8% |
Agentic & Tool Use Not comparable
GPT-5.4 nano: —, Mistral Medium: 28.3 (#90)
| Benchmark | GPT-5.4 nano | Mistral Medium |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 37.7% |
Reasoning Too close to call
GPT-5.4 nano: 23.7 (#173), Mistral Medium: 24.0 (#167)
| Benchmark | GPT-5.4 nano | Mistral Medium |
|---|---|---|
| Kagi LLM Benchmark | 39.7% | 50% |
| CritPt | 9.3% | 0% |
| LMArena Hard Prompts | 1381 | 1426 |
| DTBench | 80.3% | 75.5% |
| LMCA | 36.9% | 26.1% |
| ARC-AGI-2 | 5.7% | — |
| ARC-AGI-1 | 51.5% | — |
| Chess Puzzles | 30% | — |
| Mystery Game Puzzles | 9% | — |
| Surface Evolver Bench | — | 26.9% |
| Epoch Capabilities Index | 145.81 | — |
| ForecastBench | 57.3 | — |
Math GPT-5.4 nano leads
GPT-5.4 nano: 40.9 (#88), Mistral Medium: 28.1 (#245)
| Benchmark | GPT-5.4 nano | Mistral Medium |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 87.8% | 32.2% |
| ProofBench | 5% | 9% |
| LMArena Math | 1406 | 1408 |
| FrontierMath (Feb 2025 set) | 25.9% | 0.3% |
| FrontierMath (Tiers 1-3) | 44.9% | — |
| FrontierMath Tier 4 | 12.2% | — |
| MATH Level 5 | — | 81.6% |
| FrontierMath Tier 4 (v1) | 6.3% | — |
Knowledge GPT-5.4 nano leads
GPT-5.4 nano: 41.9 (#103), Mistral Medium: 25.0 (#265)
| Benchmark | GPT-5.4 nano | Mistral Medium |
|---|---|---|
| GPQA Diamond | 78.5% | 59.5% |
| Vectara Hallucination Rate | 3.1% | 22.7% |
| LMArena Expert | 1396 | 1408 |
| Humanity's Last Exam | — | 4.5% |
| SimpleQA Verified | 11.7% | — |
Multimodal GPT-5.4 nano leads
GPT-5.4 nano: 36.7 (#78), Mistral Medium: 35.3 (#88)
| Benchmark | GPT-5.4 nano | Mistral Medium |
|---|---|---|
| LMArena Vision | 1196 | 1172 |
Multilingual Mistral Medium leads
GPT-5.4 nano: 48.6 (#140), Mistral Medium: 52.1 (#91)
| Benchmark | GPT-5.4 nano | Mistral Medium |
|---|---|---|
| LMArena Non-English | 1359 | 1408 |
| LMArena Chinese | 1392 | 1447 |
| LMArena French | 1396 | 1459 |
| LMArena German | 1367 | 1432 |
| LMArena Japanese | 1343 | 1378 |
| LMArena Korean | 1320 | 1380 |
| LMArena Russian | 1363 | 1411 |
| LMArena Spanish | 1371 | 1433 |
Instruction Following Mistral Medium leads
GPT-5.4 nano: 71.9 (#144), Mistral Medium: 73.7 (#116)
| Benchmark | GPT-5.4 nano | Mistral Medium |
|---|---|---|
| LMArena Instruction Following | 1362 | 1398 |
Long Context Mistral Medium leads
GPT-5.4 nano: 41.6 (#137), Mistral Medium: 42.9 (#114)
| Benchmark | GPT-5.4 nano | Mistral Medium |
|---|---|---|
| LMArena Longer Query | 1366 | 1406 |
Writing & Preference Mistral Medium leads
GPT-5.4 nano: 55.7 (#142), Mistral Medium: 60.0 (#103)
| Benchmark | GPT-5.4 nano | Mistral Medium |
|---|---|---|
| LMArena Text | 1372 | 1424 |
| LMArena Creative Writing | 1314 | 1391 |
| LMArena Multi-Turn | 1382 | 1418 |
| Short-Story Creative Writing | — | 77.3% |
Frequently asked questions
Is GPT-5.4 nano better than Mistral Medium?
GPT-5.4 nano is the stronger model overall, scoring 41.9 to 36.3 on the Noometry Index.
Which is cheaper, GPT-5.4 nano or Mistral Medium?
GPT-5.4 nano is cheaper. It lists at $0.20 per million input tokens and $1.25 per million output tokens; Mistral Medium lists at $1.50 and $7.50.
Is GPT-5.4 nano or Mistral Medium better for coding?
GPT-5.4 nano scores higher on coding benchmarks: 43.6 versus 34.2 in the Noometry coding category.
Which has the bigger context window?
GPT-5.4 nano does, with 400K tokens against 262K.
How many benchmarks do GPT-5.4 nano and Mistral Medium share?
30 benchmarks have published results for both models. GPT-5.4 nano has 40 scored results on Noometry and Mistral Medium has 36.