Model comparison
Codestral vs Hy3
Hy3 is the stronger model overall, scoring 44.2 to 30.6 on the Noometry Index.
Last verified . 0 shared benchmarks.
Mistral AI
TencentSummary
- The widest gap is in coding, where Hy3 leads 46.8 to 27.3.
- Hy3 is cheaper at $0.0825 / $0.33 per million input/output tokens, against $0.30 / $0.90 for Codestral.
- Hy3 accepts more context: 262K tokens versus 256K.
- Hy3 has downloadable open weights; the other is API-only.
Side by side
| Codestral | Hy3 | |
|---|---|---|
| Provider | Mistral AI | Tencent |
| Noometry Index | 30.6 | 44.2 |
| Released | 2024-05-29 | 2026-07-06 |
| Weights | Proprietary | Open |
| Context window | 256K | 262K |
| Max output | 8K | 128K |
| Input $ / M tokens | $0.30 | $0.0825 |
| Output $ / M tokens | $0.90 | $0.33 |
| Results tracked | 7 | 19 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Hy3 leads
Codestral: 27.3 (#321), Hy3: 46.8 (#63)
| Benchmark | Codestral | Hy3 |
|---|---|---|
| Aider Polyglot | 11.1% | — |
| LMArena WebDev | — | 1508 |
| BigCodeBench Instruct | 41.8% | — |
| LMArena Coding | — | 1464 |
| BigCodeBench Complete | 52.5% | — |
| ALE-Bench | 137.78 | — |
| HumanEval+ | 73.8% | — |
| MBPP+ | 61.9% | — |
Reasoning Hy3 leads
Codestral: 19.8 (#251), Hy3: 26.1 (#136)
| Benchmark | Codestral | Hy3 |
|---|---|---|
| Kagi LLM Benchmark | 32.5% | — |
| NYT Connections (extended) | — | 41.2% |
| LMArena Hard Prompts | — | 1447 |
Math Not comparable
Codestral: —, Hy3: 40.1 (#93)
| Benchmark | Codestral | Hy3 |
|---|---|---|
| LMArena Math | — | 1475 |
Knowledge Not comparable
Codestral: —, Hy3: 40.8 (#114)
| Benchmark | Codestral | Hy3 |
|---|---|---|
| LMArena Expert | — | 1460 |
Multilingual Not comparable
Codestral: —, Hy3: 53.5 (#65)
| Benchmark | Codestral | Hy3 |
|---|---|---|
| LMArena Non-English | — | 1426 |
| LMArena Chinese | — | 1493 |
| LMArena French | — | 1461 |
| LMArena German | — | 1439 |
| LMArena Japanese | — | 1392 |
| LMArena Korean | — | 1395 |
| LMArena Russian | — | 1432 |
| LMArena Spanish | — | 1456 |
Instruction Following Not comparable
Codestral: —, Hy3: 75.1 (#70)
| Benchmark | Codestral | Hy3 |
|---|---|---|
| LMArena Instruction Following | — | 1426 |
Long Context Not comparable
Codestral: —, Hy3: 44.1 (#75)
| Benchmark | Codestral | Hy3 |
|---|---|---|
| LMArena Longer Query | — | 1442 |
Writing & Preference Not comparable
Codestral: —, Hy3: 62.2 (#81)
| Benchmark | Codestral | Hy3 |
|---|---|---|
| LMArena Text | — | 1439 |
| LMArena Creative Writing | — | 1402 |
| LMArena Multi-Turn | — | 1436 |
Frequently asked questions
Is Codestral better than Hy3?
Hy3 is the stronger model overall, scoring 44.2 to 30.6 on the Noometry Index.
Which is cheaper, Codestral or Hy3?
Hy3 is cheaper. It lists at $0.0825 per million input tokens and $0.33 per million output tokens; Codestral lists at $0.30 and $0.90.
Is Codestral or Hy3 better for coding?
Hy3 scores higher on coding benchmarks: 46.8 versus 27.3 in the Noometry coding category.
Which has the bigger context window?
Hy3 does, with 262K tokens against 256K.
How many benchmarks do Codestral and Hy3 share?
0 benchmarks have published results for both models. Codestral has 7 scored results on Noometry and Hy3 has 19.