# GPT-4.1 vs Mistral Medium

> GPT-4.1 and Mistral Medium score almost the same on the Noometry Index (35.7 vs 36.0), so choose on price, context window or the category you care about most.

- Canonical page: https://noometry.com/compare/gpt-4-1-vs-mistral-medium
- Last updated: 2026-10-10
- Shared benchmarks: 30

## Summary

- They share 30 benchmarks with published results for both. GPT-4.1 scores higher in 4 categories and Mistral Medium in 6 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where GPT-4.1 leads 37.0 to 24.9.
- The biggest single-benchmark swing is Vectara Hallucination Rate: 5.6% for GPT-4.1 and 22.7% for Mistral Medium.
- Mistral Medium is cheaper at $1.50 / $7.50 per million input/output tokens, against $2 / $8 for GPT-4.1.
- GPT-4.1 accepts more context: 1.05M tokens versus 262K.
- Mistral Medium has downloadable open weights; the other is API-only.

## Snapshot

| | GPT-4.1 | Mistral Medium |
|---|---|---|
| Provider | OpenAI | Mistral AI |
| Noometry Index | 35.7 | 36.0 |
| Rank | 215 | 211 |
| Context | 1.05M | 262K |
| Input $/M | $2 | $1.50 |
| Output $/M | $8 | $7.50 |
| Weights | Proprietary | Open |

## Coding

- GPT-4.1: 34.2 (#228)
- Mistral Medium: 33.8 (#241)

| Benchmark | GPT-4.1 | Mistral Medium |
|---|---|---|
| WeirdML | 39% | 43.7% |
| LMArena Coding | 1391 | 1434 |
| ALE-Bench | 558.1 | 763.98 |
| SWE-bench Verified | 48.5% | — |
| FrontierCode | — | 8% |
| SWE-bench Verified (bash only) | 39.6% | — |
| Aider Polyglot | 52.4% | — |
| SciCode | — | 40.2% |
| CadEval | 42% | — |

## Agentic & Tool Use

- GPT-4.1: 34.4 (#40)
- Mistral Medium: 28.1 (#84)

| Benchmark | GPT-4.1 | Mistral Medium |
|---|---|---|
| Berkeley Function Calling Leaderboard | 54% | 37.7% |

## Reasoning

- GPT-4.1: 11.7 (#334)
- Mistral Medium: 23.3 (#165)

| Benchmark | GPT-4.1 | Mistral Medium |
|---|---|---|
| Kagi LLM Benchmark | 52.3% | 50% |
| LMArena Hard Prompts | 1384 | 1426 |
| DTBench | 68.3% | 75.5% |
| LMCA | 25.6% | 26.1% |
| ARC-AGI-2 | 0.4% | — |
| SimpleBench | 27% | — |
| ARC-AGI-1 | 5.5% | — |
| CritPt | — | 0% |
| Chess Puzzles | 6% | — |
| EnigmaEval | 2.2% | — |
| Surface Evolver Bench | — | 26.9% |
| Epoch Capabilities Index | 136.79 | — |
| ForecastBench | 61.5 | — |

## Math

- GPT-4.1: 21.4 (#269)
- Mistral Medium: 27.2 (#238)

| Benchmark | GPT-4.1 | Mistral Medium |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 38.3% | 32.2% |
| LMArena Math | 1369 | 1409 |
| MATH Level 5 | 83% | 81.6% |
| FrontierMath (Feb 2025 set) | 5.5% | 0.3% |
| FrontierMath (Tiers 1-3) | 6% | — |
| ProofBench | — | 9% |
| Omni-MATH | 47.1% | — |
| FrontierMath Tier 4 (v1) | 0% | — |

## Knowledge

- GPT-4.1: 37.0 (#152)
- Mistral Medium: 24.9 (#260)

| Benchmark | GPT-4.1 | Mistral Medium |
|---|---|---|
| GPQA Diamond | 66.9% | 59.5% |
| Humanity's Last Exam | 5.4% | 4.5% |
| Vectara Hallucination Rate | 5.6% | 22.7% |
| LMArena Expert | 1364 | 1408 |
| SimpleQA Verified | 31.1% | — |
| MMLU-Pro | 81.1% | — |
| GPQA (HELM) | 65.9% | — |

## Multimodal

- GPT-4.1: 37.5 (#66)
- Mistral Medium: 34.6 (#82)

| Benchmark | GPT-4.1 | Mistral Medium |
|---|---|---|
| LMArena Vision | 1210 | 1172 |
| GeoBench | 72% | — |

## Multilingual

- GPT-4.1: 49.6 (#128)
- Mistral Medium: 52.3 (#86)

| Benchmark | GPT-4.1 | Mistral Medium |
|---|---|---|
| LMArena Non-English | 1370 | 1408 |
| LMArena Chinese | 1382 | 1448 |
| LMArena French | 1383 | 1460 |
| LMArena German | 1380 | 1433 |
| LMArena Japanese | 1320 | 1378 |
| LMArena Korean | 1339 | 1382 |
| LMArena Russian | 1377 | 1411 |
| LMArena Spanish | 1375 | 1433 |

## Instruction Following

- GPT-4.1: 71.5 (#148)
- Mistral Medium: 73.9 (#111)

| Benchmark | GPT-4.1 | Mistral Medium |
|---|---|---|
| LMArena Instruction Following | 1367 | 1398 |
| IFEval | 83.8% | — |

## Long Context

- GPT-4.1: 40.0 (#158)
- Mistral Medium: 42.9 (#108)

| Benchmark | GPT-4.1 | Mistral Medium |
|---|---|---|
| LMArena Longer Query | 1385 | 1406 |
| Fiction.LiveBench | 63.9% | — |

## Writing & Preference

- GPT-4.1: 57.8 (#120)
- Mistral Medium: 60.2 (#97)

| Benchmark | GPT-4.1 | Mistral Medium |
|---|---|---|
| LMArena Text | 1383 | 1424 |
| LMArena Creative Writing | 1363 | 1391 |
| LMArena Multi-Turn | 1398 | 1418 |
| Short-Story Creative Writing | — | 77.3% |
| EQ-Bench Creative Writing | 1420 | — |
| WildBench | 85.4% | — |

## FAQ

### Is GPT-4.1 better than Mistral Medium?

GPT-4.1 and Mistral Medium score almost the same on the Noometry Index (35.7 vs 36.0), so choose on price, context window or the category you care about most.

### Which is cheaper, GPT-4.1 or Mistral Medium?

Mistral Medium is cheaper. It lists at $1.50 per million input tokens and $7.50 per million output tokens; GPT-4.1 lists at $2 and $8.

### Is GPT-4.1 or Mistral Medium better for coding?

They score almost the same on coding (34.2 vs 33.8); 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 Medium share?

30 benchmarks have published results for both models. GPT-4.1 has 52 scored results on Noometry and Mistral Medium has 36.