Model comparison
GPT-5 Nano vs Mistral Large 4
Mistral Large 4 is the stronger model overall, scoring 43.1 to 33.5 on the Noometry Index. GPT-5 Nano costs 7.5× less per token, which makes it the better buy when Mistral Large 4's lead doesn't matter for your workload.
Last verified . 13 shared benchmarks.
Mistral AISummary
- They share 13 benchmarks with published results for both. GPT-5 Nano scores higher in 0 categories and Mistral Large 4 in 8 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Mistral Large 4 leads 60.4 to 39.1.
- The biggest single-benchmark swing is SimpleQA Verified: 11.7% for GPT-5 Nano and 20% for Mistral Large 4.
- GPT-5 Nano is cheaper at $0.05 / $0.40 per million input/output tokens, against $0.68 / $2.09 for Mistral Large 4.
- Mistral Large 4 accepts more context: 1.05M tokens versus 400K.
Side by side
| GPT-5 Nano | Mistral Large 4 | |
|---|---|---|
| Provider | OpenAI | Mistral AI |
| Noometry Index | 33.5 | 43.1 |
| Released | 2025-08-07 | 2026-10-06 |
| Weights | Proprietary | Proprietary |
| Context window | 400K | 1.05M |
| Max output | 128K | 262K |
| Input $ / M tokens | $0.05 | $0.68 |
| Output $ / M tokens | $0.40 | $2.09 |
| Results tracked | 49 | 15 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Mistral Large 4 leads
GPT-5 Nano: 33.6 (#254), Mistral Large 4: 48.6 (#57)
| Benchmark | GPT-5 Nano | Mistral Large 4 |
|---|---|---|
| LMArena Coding | 1351 | 1475 |
| SWE-bench Verified (bash only) | 34.8% | — |
| LMArena WebDev | — | 1541 |
| WeirdML | 38.1% | — |
| ALE-Bench | 718.67 | — |
Agentic & Tool Use Not comparable
GPT-5 Nano: 25.8 (#106), Mistral Large 4: —
| Benchmark | GPT-5 Nano | Mistral Large 4 |
|---|---|---|
| Terminal-Bench | 21.8% | — |
| Berkeley Function Calling Leaderboard | 51.5% | — |
Reasoning Mistral Large 4 leads
GPT-5 Nano: 16.3 (#306), Mistral Large 4: 22.5 (#192)
| Benchmark | GPT-5 Nano | Mistral Large 4 |
|---|---|---|
| LMArena Hard Prompts | 1328 | 1444 |
| ARC-AGI-2 | 2.6% | — |
| Kagi LLM Benchmark | 62.2% | — |
| NYT Connections (extended) | — | 27.4% |
| ARC-AGI-1 | 20.7% | — |
| Chess Puzzles | 27% | — |
| Mystery Game Puzzles | 9% | — |
| DTBench | 62.7% | — |
| LMCA | 7.9% | — |
| Epoch Capabilities Index | 139.38 | — |
| ForecastBench | 59.1 | — |
Math Mistral Large 4 leads
GPT-5 Nano: 29.4 (#241), Mistral Large 4: 40.4 (#91)
| Benchmark | GPT-5 Nano | Mistral Large 4 |
|---|---|---|
| LMArena Math | 1317 | 1488 |
| FrontierMath (Tiers 1-3) | 20% | — |
| FrontierMath Tier 4 | 2.4% | — |
| OTIS Mock AIME 2024-2025 | 81.1% | — |
| ProofBench | 12% | — |
| Omni-MATH | 54.6% | — |
| MATH Level 5 | 95.2% | — |
| FrontierMath (Feb 2025 set) | 8.3% | — |
| FrontierMath Tier 4 (v1) | 2.1% | — |
Knowledge Too close to call
GPT-5 Nano: 35.9 (#178), Mistral Large 4: 36.6 (#166)
| Benchmark | GPT-5 Nano | Mistral Large 4 |
|---|---|---|
| SimpleQA Verified | 11.7% | 20% |
| LMArena Expert | 1321 | 1447 |
| GPQA Diamond | 69.4% | — |
| MMLU-Pro | 77.8% | — |
| Vectara Hallucination Rate | 10.5% | — |
| GPQA (HELM) | 67.9% | — |
Multimodal Not comparable
GPT-5 Nano: 31.3 (#108), Mistral Large 4: —
| Benchmark | GPT-5 Nano | Mistral Large 4 |
|---|---|---|
| LMArena Vision | 1159 | — |
| VPCT | 37.2% | — |
Multilingual Mistral Large 4 leads
GPT-5 Nano: 45.3 (#172), Mistral Large 4: 52.6 (#82)
| Benchmark | GPT-5 Nano | Mistral Large 4 |
|---|---|---|
| LMArena Non-English | 1313 | 1415 |
| LMArena Chinese | 1356 | 1491 |
| LMArena Russian | 1296 | 1414 |
| LMArena German | 1327 | — |
| LMArena Japanese | 1226 | — |
| LMArena Korean | 1269 | — |
| LMArena Spanish | 1360 | — |
Instruction Following Too close to call
GPT-5 Nano: 75.0 (#79), Mistral Large 4: 75.0 (#76)
| Benchmark | GPT-5 Nano | Mistral Large 4 |
|---|---|---|
| LMArena Instruction Following | 1306 | 1424 |
| IFEval | 93.2% | — |
Long Context Mistral Large 4 leads
GPT-5 Nano: 31.3 (#281), Mistral Large 4: 43.6 (#89)
| Benchmark | GPT-5 Nano | Mistral Large 4 |
|---|---|---|
| LMArena Longer Query | 1312 | 1429 |
| Fiction.LiveBench | 44.4% | — |
Writing & Preference Mistral Large 4 leads
GPT-5 Nano: 39.1 (#249), Mistral Large 4: 60.4 (#97)
| Benchmark | GPT-5 Nano | Mistral Large 4 |
|---|---|---|
| LMArena Text | 1320 | 1427 |
| LMArena Creative Writing | 1249 | 1361 |
| LMArena Multi-Turn | 1311 | 1424 |
| EQ-Bench Creative Writing | 705 | — |
| WildBench | 80.6% | — |
Frequently asked questions
Is GPT-5 Nano better than Mistral Large 4?
Mistral Large 4 is the stronger model overall, scoring 43.1 to 33.5 on the Noometry Index. GPT-5 Nano costs 7.5× less per token, which makes it the better buy when Mistral Large 4's lead doesn't matter for your workload.
Which is cheaper, GPT-5 Nano or Mistral Large 4?
GPT-5 Nano is cheaper. It lists at $0.05 per million input tokens and $0.40 per million output tokens; Mistral Large 4 lists at $0.68 and $2.09.
Is GPT-5 Nano or Mistral Large 4 better for coding?
Mistral Large 4 scores higher on coding benchmarks: 48.6 versus 33.6 in the Noometry coding category.
Which has the bigger context window?
Mistral Large 4 does, with 1.05M tokens against 400K.
How many benchmarks do GPT-5 Nano and Mistral Large 4 share?
13 benchmarks have published results for both models. GPT-5 Nano has 49 scored results on Noometry and Mistral Large 4 has 15.