Model comparison
GPT-4.1 vs Mistral Small
GPT-4.1 is the stronger model overall, scoring 35.9 to 33.4 on the Noometry Index. Mistral Small costs 13× less per token, which makes it the better buy when GPT-4.1's lead doesn't matter for your workload.
Last verified . 27 shared benchmarks.
Mistral AISummary
- They share 27 benchmarks with published results for both. GPT-4.1 scores higher in 8 categories and Mistral Small in 2 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Mistral Small leads 19.8 to 11.7.
- The biggest single-benchmark swing is MATH Level 5: 83% for GPT-4.1 and 46.8% for Mistral Small.
- Mistral Small is cheaper at $0.15 / $0.60 per million input/output tokens, against $2 / $8 for GPT-4.1.
- GPT-4.1 accepts more context: 1.05M tokens versus 262K.
- Mistral Small has downloadable open weights; the other is API-only.
Side by side
| GPT-4.1 | Mistral Small | |
|---|---|---|
| Provider | OpenAI | Mistral AI |
| Noometry Index | 35.9 | 33.4 |
| Released | 2025-04-14 | 2024-02-26 |
| Weights | Proprietary | Open |
| Context window | 1.05M | 262K |
| Max output | 33K | 256K |
| Input $ / M tokens | $2 | $0.15 |
| Output $ / M tokens | $8 | $0.60 |
| Results tracked | 52 | 39 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
GPT-4.1: 34.4 (#238), Mistral Small: 34.0 (#247)
| Benchmark | GPT-4.1 | Mistral Small |
|---|---|---|
| LMArena Coding | 1391 | 1362 |
| ALE-Bench | 558.1 | 497.62 |
| SWE-bench Verified | 48.5% | — |
| SWE-bench Verified (bash only) | 39.6% | — |
| Aider Polyglot | 52.4% | — |
| SciCode | — | 26.5% |
| WeirdML | 39% | — |
| BigCodeBench Instruct | — | 36.1% |
| LiveBench Coding | — | 36.2% |
| BigCodeBench Complete | — | 46.6% |
| CadEval | 42% | — |
Agentic & Tool Use GPT-4.1 leads
GPT-4.1: 34.7 (#43), Mistral Small: 28.1 (#93)
| Benchmark | GPT-4.1 | Mistral Small |
|---|---|---|
| Berkeley Function Calling Leaderboard | 54% | 37.1% |
Reasoning Mistral Small leads
GPT-4.1: 11.7 (#339), Mistral Small: 19.8 (#250)
| Benchmark | GPT-4.1 | Mistral Small |
|---|---|---|
| Kagi LLM Benchmark | 52.3% | 37.8% |
| LMArena Hard Prompts | 1384 | 1335 |
| DTBench | 68.3% | 70.9% |
| LMCA | 25.6% | 20.6% |
| ARC-AGI-2 | 0.4% | — |
| SimpleBench | 27% | — |
| ARC-AGI-1 | 5.5% | — |
| CritPt | — | 0% |
| Chess Puzzles | 6% | — |
| EnigmaEval | 2.2% | — |
| LiveBench Reasoning | — | 44.8% |
| LiveBench Data Analysis | — | 53.7% |
| Epoch Capabilities Index | 136.78 | — |
| ForecastBench | 61.5 | — |
| LiveBench | — | 44% |
Math GPT-4.1 leads
GPT-4.1: 22.3 (#280), Mistral Small: 16.4 (#293)
| Benchmark | GPT-4.1 | Mistral Small |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 38.3% | 5.8% |
| LMArena Math | 1370 | 1341 |
| MATH Level 5 | 83% | 46.8% |
| FrontierMath (Tiers 1-3) | 6% | — |
| Omni-MATH | 47.1% | — |
| LiveBench Math | — | 39.9% |
| FrontierMath (Feb 2025 set) | 5.5% | — |
| FrontierMath Tier 4 (v1) | 0% | — |
Knowledge GPT-4.1 leads
GPT-4.1: 37.1 (#160), Mistral Small: 31.0 (#222)
| Benchmark | GPT-4.1 | Mistral Small |
|---|---|---|
| GPQA Diamond | 66.9% | 47.5% |
| Vectara Hallucination Rate | 5.6% | 5.1% |
| LMArena Expert | 1364 | 1291 |
| Humanity's Last Exam | 5.4% | — |
| SimpleQA Verified | 31.1% | — |
| MMLU-Pro | 81.1% | — |
| GPQA (HELM) | 65.9% | — |
| MMLU | — | 68.7% |
Multimodal GPT-4.1 leads
GPT-4.1: 38.2 (#67), Mistral Small: 33.5 (#96)
| Benchmark | GPT-4.1 | Mistral Small |
|---|---|---|
| LMArena Vision | 1211 | 1142 |
| GeoBench | 72% | — |
Multilingual GPT-4.1 leads
GPT-4.1: 49.4 (#133), Mistral Small: 45.5 (#169)
| Benchmark | GPT-4.1 | Mistral Small |
|---|---|---|
| LMArena Non-English | 1370 | 1315 |
| LMArena Chinese | 1382 | 1340 |
| LMArena French | 1382 | 1337 |
| LMArena German | 1381 | 1340 |
| LMArena Japanese | 1319 | 1275 |
| LMArena Korean | 1339 | 1259 |
| LMArena Russian | 1377 | 1324 |
| LMArena Spanish | 1376 | 1346 |
Instruction Following GPT-4.1 leads
GPT-4.1: 71.3 (#153), Mistral Small: 66.4 (#209)
| Benchmark | GPT-4.1 | Mistral Small |
|---|---|---|
| LMArena Instruction Following | 1367 | 1310 |
| LiveBench Instruction Following | — | 63.7% |
| IFEval | 83.8% | — |
Long Context Too close to call
GPT-4.1: 40.0 (#163), Mistral Small: 40.4 (#156)
| Benchmark | GPT-4.1 | Mistral Small |
|---|---|---|
| LMArena Longer Query | 1385 | 1327 |
| Fiction.LiveBench | 63.9% | — |
Writing & Preference GPT-4.1 leads
GPT-4.1: 57.6 (#125), Mistral Small: 52.5 (#171)
| Benchmark | GPT-4.1 | Mistral Small |
|---|---|---|
| LMArena Text | 1383 | 1338 |
| LMArena Creative Writing | 1363 | 1305 |
| LMArena Multi-Turn | 1398 | 1344 |
| EQ-Bench Creative Writing | 1420 | — |
| WildBench | 85.4% | — |
| LiveBench Language | — | 30.5% |
Frequently asked questions
Is GPT-4.1 better than Mistral Small?
GPT-4.1 is the stronger model overall, scoring 35.9 to 33.4 on the Noometry Index. Mistral Small costs 13× less per token, which makes it the better buy when GPT-4.1's lead doesn't matter for your workload.
Which is cheaper, GPT-4.1 or Mistral Small?
Mistral Small is cheaper. It lists at $0.15 per million input tokens and $0.60 per million output tokens; GPT-4.1 lists at $2 and $8.
Is GPT-4.1 or Mistral Small better for coding?
They score almost the same on coding (34.4 vs 34.0); test both on your own repository before choosing.
Which has the bigger context window?
GPT-4.1 does, with 1.05M tokens against 262K.
How many benchmarks do GPT-4.1 and Mistral Small share?
27 benchmarks have published results for both models. GPT-4.1 has 52 scored results on Noometry and Mistral Small has 39.