# Hy3 vs Mistral Large

> Hy3 is the stronger model overall, scoring 44.2 to 31.9 on the Noometry Index.

- Canonical page: https://noometry.com/compare/hy3-vs-mistral-large
- Last updated: 2026-10-11
- Shared benchmarks: 17

## Summary

- They share 17 benchmarks with published results for both. Hy3 scores higher in 8 categories and Mistral Large in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Hy3 leads 40.1 to 18.2.
- Hy3 is cheaper at $0.13 / $0.53 per million input/output tokens, against $2 / $6 for Mistral Large.
- Hy3 accepts more context: 262K tokens versus 131K.

## Snapshot

| | Hy3 | Mistral Large |
|---|---|---|
| Provider | Tencent | Mistral AI |
| Noometry Index | 44.2 | 31.9 |
| Rank | 79 | 263 |
| Context | 262K | 131K |
| Input $/M | $0.13 | $2 |
| Output $/M | $0.53 | $6 |
| Weights | Open | Open |

## Coding

- Hy3: 46.8 (#63)
- Mistral Large: 34.3 (#240)

| Benchmark | Hy3 | Mistral Large |
|---|---|---|
| LMArena Coding | 1464 | 1277 |
| LMArena WebDev | 1508 | — |
| SciCode | — | 36.2% |
| BigCodeBench Instruct | — | 30% |
| LiveBench Coding | — | 47.1% |
| BigCodeBench Complete | — | 38.3% |
| ALE-Bench | — | 264.7 |
| HumanEval+ | — | 62.2% |
| MBPP+ | — | 59.5% |

## Agentic & Tool Use

- Hy3: —
- Mistral Large: 28.6 (#89)

| Benchmark | Hy3 | Mistral Large |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 38.4% |

## Reasoning

- Hy3: 26.1 (#136)
- Mistral Large: 15.8 (#310)

| Benchmark | Hy3 | Mistral Large |
|---|---|---|
| LMArena Hard Prompts | 1447 | 1257 |
| SimpleBench | — | 22.5% |
| NYT Connections (extended) | 41.2% | — |
| CritPt | — | 0% |
| LiveBench Reasoning | — | 43.5% |
| DTBench | — | 65.1% |
| LiveBench Data Analysis | — | 50.1% |
| LMCA | — | 16.7% |
| Epoch Capabilities Index | — | 128.52 |
| ForecastBench | — | 57.1 |
| LiveBench | — | 48.4% |

## Math

- Hy3: 40.1 (#93)
- Mistral Large: 18.2 (#291)

| Benchmark | Hy3 | Mistral Large |
|---|---|---|
| LMArena Math | 1475 | 1262 |
| OTIS Mock AIME 2024-2025 | — | 8.5% |
| Omni-MATH | — | 28.1% |
| LiveBench Math | — | 42.5% |
| MATH Level 5 | — | 50.3% |
| FrontierMath (Feb 2025 set) | — | 0.3% |

## Knowledge

- Hy3: 40.8 (#114)
- Mistral Large: 30.1 (#230)

| Benchmark | Hy3 | Mistral Large |
|---|---|---|
| LMArena Expert | 1460 | 1232 |
| GPQA Diamond | — | 51.3% |
| MMLU-Pro | — | 59.9% |
| Confabulations | — | 21.4% |
| Vectara Hallucination Rate | — | 4.5% |
| GPQA (HELM) | — | 43.5% |
| MMLU | — | 80% |

## Multilingual

- Hy3: 53.5 (#65)
- Mistral Large: 40.0 (#219)

| Benchmark | Hy3 | Mistral Large |
|---|---|---|
| LMArena Non-English | 1426 | 1237 |
| LMArena Chinese | 1493 | 1240 |
| LMArena French | 1461 | 1325 |
| LMArena German | 1439 | 1254 |
| LMArena Japanese | 1392 | 1188 |
| LMArena Korean | 1395 | 1202 |
| LMArena Russian | 1432 | 1257 |
| LMArena Spanish | 1456 | 1268 |

## Instruction Following

- Hy3: 75.1 (#70)
- Mistral Large: 67.9 (#191)

| Benchmark | Hy3 | Mistral Large |
|---|---|---|
| LMArena Instruction Following | 1426 | 1249 |
| LiveBench Instruction Following | — | 67.9% |
| IFEval | — | 87.7% |

## Long Context

- Hy3: 44.1 (#75)
- Mistral Large: 38.3 (#199)

| Benchmark | Hy3 | Mistral Large |
|---|---|---|
| LMArena Longer Query | 1442 | 1261 |

## Writing & Preference

- Hy3: 62.2 (#81)
- Mistral Large: 40.7 (#242)

| Benchmark | Hy3 | Mistral Large |
|---|---|---|
| LMArena Text | 1439 | 1266 |
| LMArena Creative Writing | 1402 | 1243 |
| LMArena Multi-Turn | 1436 | 1260 |
| Short-Story Creative Writing | — | 69% |
| EQ-Bench Creative Writing | — | 985 |
| WildBench | — | 80.1% |
| LiveBench Language | — | 39.4% |

## FAQ

### Is Hy3 better than Mistral Large?

Hy3 is the stronger model overall, scoring 44.2 to 31.9 on the Noometry Index.

### Which is cheaper, Hy3 or Mistral Large?

Hy3 is cheaper. It lists at $0.13 per million input tokens and $0.53 per million output tokens; Mistral Large lists at $2 and $6.

### Is Hy3 or Mistral Large better for coding?

Hy3 scores higher on coding benchmarks: 46.8 versus 34.3 in the Noometry coding category.

### Which has the bigger context window?

Hy3 does, with 262K tokens against 131K.

### How many benchmarks do Hy3 and Mistral Large share?

17 benchmarks have published results for both models. Hy3 has 19 scored results on Noometry and Mistral Large has 51.