# Gemini 2.5 Pro vs Mistral Large

> Gemini 2.5 Pro is the stronger model overall, scoring 45.0 to 31.9 on the Noometry Index.

- Canonical page: https://noometry.com/compare/gemini-2-5-pro-vs-mistral-large
- Last updated: 2026-10-11
- Shared benchmarks: 45

## Summary

- They share 45 benchmarks with published results for both. Gemini 2.5 Pro scores higher in 9 categories and Mistral Large in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Gemini 2.5 Pro leads 56.0 to 30.1.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 84.7% for Gemini 2.5 Pro and 8.5% for Mistral Large.
- Mistral Large is cheaper at $2 / $6 per million input/output tokens, against $1.25 / $10 for Gemini 2.5 Pro.
- Gemini 2.5 Pro accepts more context: 1.05M tokens versus 131K.
- Mistral Large has downloadable open weights; the other is API-only.

## Snapshot

| | Gemini 2.5 Pro | Mistral Large |
|---|---|---|
| Provider | Google | Mistral AI |
| Noometry Index | 45.0 | 31.9 |
| Rank | 75 | 263 |
| Context | 1.05M | 131K |
| Input $/M | $1.25 | $2 |
| Output $/M | $10 | $6 |
| Weights | Proprietary | Open |

## Coding

- Gemini 2.5 Pro: 42.4 (#101)
- Mistral Large: 34.3 (#240)

| Benchmark | Gemini 2.5 Pro | Mistral Large |
|---|---|---|
| SciCode | 42.8% | 36.2% |
| LiveBench Coding | 85.9% | 47.1% |
| LMArena Coding | 1452 | 1277 |
| ALE-Bench | 785.52 | 264.7 |
| SWE-bench Verified | 57.6% | — |
| SWE-bench Verified (bash only) | 53.6% | — |
| Aider Polyglot | 83.1% | — |
| LMArena WebDev | 1227 | — |
| GSO | 3.9% | — |
| WeirdML | 54% | — |
| BigCodeBench Instruct | — | 30% |
| BigCodeBench Complete | — | 38.3% |
| CadEval | 64% | — |
| AlgoTune | 1.51 | — |
| HumanEval+ | — | 62.2% |
| MBPP+ | — | 59.5% |

## Agentic & Tool Use

- Gemini 2.5 Pro: 29.2 (#88)
- Mistral Large: 28.6 (#89)

| Benchmark | Gemini 2.5 Pro | Mistral Large |
|---|---|---|
| Terminal-Bench | 32.6% | — |
| Berkeley Function Calling Leaderboard | — | 38.4% |
| GDPval | 23.3% | — |
| Remote Labor Index | 0.8% | — |
| TheAgentCompany | 30.3% | — |
| τ²-bench Banking | 13.7% | — |
| DeepResearch Bench | 42.8% | — |
| BALROG | 43.3% | — |
| LMArena Search | 1142 | — |
| METR Time Horizons | 55.4% | — |
| Vending-Bench 2 | 573.64 | — |

## Reasoning

- Gemini 2.5 Pro: 28.8 (#99)
- Mistral Large: 15.8 (#310)

| Benchmark | Gemini 2.5 Pro | Mistral Large |
|---|---|---|
| SimpleBench | 62.4% | 22.5% |
| CritPt | 2% | 0% |
| LiveBench Reasoning | 89.8% | 43.5% |
| LMArena Hard Prompts | 1455 | 1257 |
| DTBench | 82.4% | 65.1% |
| LiveBench Data Analysis | 79.9% | 50.1% |
| LMCA | 34.8% | 16.7% |
| Epoch Capabilities Index | 145.32 | 128.52 |
| ForecastBench | 61.3 | 57.1 |
| LiveBench | 82.3% | 48.4% |
| ARC-AGI-2 | 4.9% | — |
| Kagi LLM Benchmark | 70.3% | — |
| ARC-AGI-1 | 41% | — |
| Chess Puzzles | 20% | — |
| EnigmaEval | 5.6% | — |

## Math

- Gemini 2.5 Pro: 32.5 (#213)
- Mistral Large: 18.2 (#291)

| Benchmark | Gemini 2.5 Pro | Mistral Large |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 84.7% | 8.5% |
| Omni-MATH | 41.6% | 28.1% |
| LiveBench Math | 90.2% | 42.5% |
| LMArena Math | 1450 | 1262 |
| MATH Level 5 | 95.9% | 50.3% |
| FrontierMath (Feb 2025 set) | 14.1% | 0.3% |
| FrontierMath (Tiers 1-3) | 24.6% | — |
| FrontierMath Tier 4 | 0% | — |
| FrontierMath Tier 4 (v1) | 4.2% | — |

## Knowledge

- Gemini 2.5 Pro: 56.0 (#46)
- Mistral Large: 30.1 (#230)

| Benchmark | Gemini 2.5 Pro | Mistral Large |
|---|---|---|
| GPQA Diamond | 85.3% | 51.3% |
| MMLU-Pro | 86.3% | 59.9% |
| Confabulations | 10.6% | 21.4% |
| Vectara Hallucination Rate | 7% | 4.5% |
| GPQA (HELM) | 74.9% | 43.5% |
| LMArena Expert | 1452 | 1232 |
| Humanity's Last Exam | 21.6% | — |
| MMLU | — | 80% |

## Multimodal

- Gemini 2.5 Pro: 45.2 (#18)
- Mistral Large: —

| Benchmark | Gemini 2.5 Pro | Mistral Large |
|---|---|---|
| LMArena Vision | 1263 | — |
| GeoBench | 86% | — |
| VPCT | 48% | — |
| LMArena Document | 1421 | — |
| SpatialViz-Bench | 44.7% | — |

## Multilingual

- Gemini 2.5 Pro: 55.3 (#31)
- Mistral Large: 40.0 (#219)

| Benchmark | Gemini 2.5 Pro | Mistral Large |
|---|---|---|
| LMArena Non-English | 1451 | 1237 |
| LMArena Chinese | 1507 | 1240 |
| LMArena French | 1472 | 1325 |
| LMArena German | 1487 | 1254 |
| LMArena Japanese | 1461 | 1188 |
| LMArena Korean | 1434 | 1202 |
| LMArena Russian | 1461 | 1257 |
| LMArena Spanish | 1473 | 1268 |

## Instruction Following

- Gemini 2.5 Pro: 75.0 (#75)
- Mistral Large: 67.9 (#191)

| Benchmark | Gemini 2.5 Pro | Mistral Large |
|---|---|---|
| LiveBench Instruction Following | 80.6% | 67.9% |
| IFEval | 84% | 87.7% |
| LMArena Instruction Following | 1437 | 1249 |

## Long Context

- Gemini 2.5 Pro: 59.8 (#5)
- Mistral Large: 38.3 (#199)

| Benchmark | Gemini 2.5 Pro | Mistral Large |
|---|---|---|
| LMArena Longer Query | 1449 | 1261 |
| Fiction.LiveBench | 91.7% | — |

## Writing & Preference

- Gemini 2.5 Pro: 63.7 (#62)
- Mistral Large: 40.7 (#242)

| Benchmark | Gemini 2.5 Pro | Mistral Large |
|---|---|---|
| LMArena Text | 1458 | 1266 |
| LMArena Creative Writing | 1454 | 1243 |
| Short-Story Creative Writing | 83.8% | 69% |
| EQ-Bench Creative Writing | 1421 | 985 |
| WildBench | 85.7% | 80.1% |
| LMArena Multi-Turn | 1453 | 1260 |
| LiveBench Language | 67.8% | 39.4% |

## FAQ

### Is Gemini 2.5 Pro better than Mistral Large?

Gemini 2.5 Pro is the stronger model overall, scoring 45.0 to 31.9 on the Noometry Index.

### Which is cheaper, Gemini 2.5 Pro or Mistral Large?

Mistral Large is cheaper. It lists at $2 per million input tokens and $6 per million output tokens; Gemini 2.5 Pro lists at $1.25 and $10.

### Is Gemini 2.5 Pro or Mistral Large better for coding?

Gemini 2.5 Pro scores higher on coding benchmarks: 42.4 versus 34.3 in the Noometry coding category.

### Which has the bigger context window?

Gemini 2.5 Pro does, with 1.05M tokens against 131K.

### How many benchmarks do Gemini 2.5 Pro and Mistral Large share?

45 benchmarks have published results for both models. Gemini 2.5 Pro has 78 scored results on Noometry and Mistral Large has 51.