Model comparison
GPT-4.1 nano vs Mistral Large
Mistral Large is the stronger model overall, scoring 31.9 to 27.9 on the Noometry Index. GPT-4.1 nano costs 17× less per token, which makes it the better buy when Mistral Large's lead doesn't matter for your workload.
Last verified . 30 shared benchmarks.
Mistral AISummary
- They share 30 benchmarks with published results for both. GPT-4.1 nano scores higher in 2 categories and Mistral Large in 7 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in long context, where Mistral Large leads 38.3 to 23.7.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 28.9% for GPT-4.1 nano and 8.5% for Mistral Large.
- GPT-4.1 nano is cheaper at $0.10 / $0.40 per million input/output tokens, against $2 / $6 for Mistral Large.
- GPT-4.1 nano accepts more context: 1.05M tokens versus 131K.
- Mistral Large has downloadable open weights; the other is API-only.
Side by side
| GPT-4.1 nano | Mistral Large | |
|---|---|---|
| Provider | OpenAI | Mistral AI |
| Noometry Index | 27.9 | 31.9 |
| Released | 2025-04-14 | 2024-02-26 |
| Weights | Proprietary | Open |
| Context window | 1.05M | 131K |
| Max output | 33K | 16K |
| Input $ / M tokens | $0.10 | $2 |
| Output $ / M tokens | $0.40 | $6 |
| Results tracked | 38 | 51 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Mistral Large leads
GPT-4.1 nano: 24.1 (#330), Mistral Large: 34.3 (#240)
| Benchmark | GPT-4.1 nano | Mistral Large |
|---|---|---|
| SciCode | 25.9% | 36.2% |
| LMArena Coding | 1306 | 1277 |
| Aider Polyglot | 8.9% | — |
| WeirdML | 19% | — |
| BigCodeBench Instruct | — | 30% |
| LiveBench Coding | — | 47.1% |
| BigCodeBench Complete | — | 38.3% |
| ALE-Bench | — | 264.7 |
| HumanEval+ | — | 62.2% |
| MBPP+ | — | 59.5% |
Agentic & Tool Use Mistral Large leads
GPT-4.1 nano: 26.5 (#104), Mistral Large: 28.6 (#89)
| Benchmark | GPT-4.1 nano | Mistral Large |
|---|---|---|
| Berkeley Function Calling Leaderboard | 33% | 38.4% |
Reasoning Mistral Large leads
GPT-4.1 nano: 8.5 (#349), Mistral Large: 15.8 (#310)
| Benchmark | GPT-4.1 nano | Mistral Large |
|---|---|---|
| CritPt | 0% | 0% |
| LMArena Hard Prompts | 1286 | 1257 |
| DTBench | 52.5% | 65.1% |
| LMCA | 5.5% | 16.7% |
| Epoch Capabilities Index | 129.62 | 128.52 |
| ARC-AGI-2 | 0% | — |
| SimpleBench | — | 22.5% |
| Kagi LLM Benchmark | 33.3% | — |
| ARC-AGI-1 | 0% | — |
| LiveBench Reasoning | — | 43.5% |
| LiveBench Data Analysis | — | 50.1% |
| ForecastBench | — | 57.1 |
| LiveBench | — | 48.4% |
Math GPT-4.1 nano leads
GPT-4.1 nano: 26.9 (#252), Mistral Large: 18.2 (#291)
| Benchmark | GPT-4.1 nano | Mistral Large |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 28.9% | 8.5% |
| Omni-MATH | 36.7% | 28.1% |
| LMArena Math | 1274 | 1262 |
| MATH Level 5 | 70% | 50.3% |
| FrontierMath (Feb 2025 set) | 1% | 0.3% |
| LiveBench Math | — | 42.5% |
Knowledge Mistral Large leads
GPT-4.1 nano: 21.8 (#273), Mistral Large: 30.1 (#230)
| Benchmark | GPT-4.1 nano | Mistral Large |
|---|---|---|
| GPQA Diamond | 48.9% | 51.3% |
| MMLU-Pro | 55% | 59.9% |
| GPQA (HELM) | 50.7% | 43.5% |
| LMArena Expert | 1272 | 1232 |
| SimpleQA Verified | 6% | — |
| Confabulations | — | 21.4% |
| Vectara Hallucination Rate | — | 4.5% |
| MMLU | — | 80% |
Multimodal Not comparable
GPT-4.1 nano: 29.2 (#113), Mistral Large: —
| Benchmark | GPT-4.1 nano | Mistral Large |
|---|---|---|
| LMArena Vision | 1063 | — |
Multilingual GPT-4.1 nano leads
GPT-4.1 nano: 41.6 (#205), Mistral Large: 40.0 (#219)
| Benchmark | GPT-4.1 nano | Mistral Large |
|---|---|---|
| LMArena Non-English | 1260 | 1237 |
| LMArena Chinese | 1270 | 1240 |
| LMArena German | 1288 | 1254 |
| LMArena Japanese | 1198 | 1188 |
| LMArena Russian | 1261 | 1257 |
| LMArena French | — | 1325 |
| LMArena Korean | — | 1202 |
| LMArena Spanish | — | 1268 |
Instruction Following Too close to call
GPT-4.1 nano: 67.8 (#193), Mistral Large: 67.9 (#191)
| Benchmark | GPT-4.1 nano | Mistral Large |
|---|---|---|
| IFEval | 84.3% | 87.7% |
| LMArena Instruction Following | 1267 | 1249 |
| LiveBench Instruction Following | — | 67.9% |
Long Context Mistral Large leads
GPT-4.1 nano: 23.7 (#296), Mistral Large: 38.3 (#199)
| Benchmark | GPT-4.1 nano | Mistral Large |
|---|---|---|
| LMArena Longer Query | 1283 | 1261 |
| Fiction.LiveBench | 25% | — |
Writing & Preference Too close to call
GPT-4.1 nano: 40.5 (#243), Mistral Large: 40.7 (#242)
| Benchmark | GPT-4.1 nano | Mistral Large |
|---|---|---|
| LMArena Text | 1285 | 1266 |
| LMArena Creative Writing | 1260 | 1243 |
| EQ-Bench Creative Writing | 946 | 985 |
| WildBench | 81.2% | 80.1% |
| LMArena Multi-Turn | 1277 | 1260 |
| Short-Story Creative Writing | — | 69% |
| LiveBench Language | — | 39.4% |
Frequently asked questions
Is GPT-4.1 nano better than Mistral Large?
Mistral Large is the stronger model overall, scoring 31.9 to 27.9 on the Noometry Index. GPT-4.1 nano costs 17× less per token, which makes it the better buy when Mistral Large's lead doesn't matter for your workload.
Which is cheaper, GPT-4.1 nano or Mistral Large?
GPT-4.1 nano is cheaper. It lists at $0.10 per million input tokens and $0.40 per million output tokens; Mistral Large lists at $2 and $6.
Is GPT-4.1 nano or Mistral Large better for coding?
Mistral Large scores higher on coding benchmarks: 34.3 versus 24.1 in the Noometry coding category.
Which has the bigger context window?
GPT-4.1 nano does, with 1.05M tokens against 131K.
How many benchmarks do GPT-4.1 nano and Mistral Large share?
30 benchmarks have published results for both models. GPT-4.1 nano has 38 scored results on Noometry and Mistral Large has 51.