Model comparison
Codestral vs Kimi K2.5 Instant
Kimi K2.5 Instant is the stronger model overall, scoring 43.6 to 30.6 on the Noometry Index.
Last verified . 0 shared benchmarks.
Mistral AISummary
- The widest gap is in coding, where Kimi K2.5 Instant leads 42.6 to 27.3.
- Kimi K2.5 Instant has downloadable open weights; the other is API-only.
Side by side
| Codestral | Kimi K2.5 Instant | |
|---|---|---|
| Provider | Mistral AI | Moonshot AI |
| Noometry Index | 30.6 | 43.6 |
| Released | 2024-05-29 | — |
| Weights | Proprietary | Open |
| Context window | 256K | — |
| Max output | 8K | — |
| Input $ / M tokens | $0.30 | — |
| Output $ / M tokens | $0.90 | — |
| Results tracked | 7 | 18 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Kimi K2.5 Instant leads
Codestral: 27.3 (#321), Kimi K2.5 Instant: 42.6 (#97)
| Benchmark | Codestral | Kimi K2.5 Instant |
|---|---|---|
| Aider Polyglot | 11.1% | — |
| LMArena WebDev | — | 1404 |
| BigCodeBench Instruct | 41.8% | — |
| LMArena Coding | — | 1484 |
| BigCodeBench Complete | 52.5% | — |
| ALE-Bench | 137.78 | — |
| HumanEval+ | 73.8% | — |
| MBPP+ | 61.9% | — |
Reasoning Kimi K2.5 Instant leads
Codestral: 19.8 (#251), Kimi K2.5 Instant: 29.7 (#90)
| Benchmark | Codestral | Kimi K2.5 Instant |
|---|---|---|
| Kagi LLM Benchmark | 32.5% | — |
| LMArena Hard Prompts | — | 1443 |
Math Not comparable
Codestral: —, Kimi K2.5 Instant: 39.4 (#105)
| Benchmark | Codestral | Kimi K2.5 Instant |
|---|---|---|
| LMArena Math | — | 1442 |
Knowledge Not comparable
Codestral: —, Kimi K2.5 Instant: 40.2 (#123)
| Benchmark | Codestral | Kimi K2.5 Instant |
|---|---|---|
| LMArena Expert | — | 1440 |
Multimodal Not comparable
Codestral: —, Kimi K2.5 Instant: 40.2 (#50)
| Benchmark | Codestral | Kimi K2.5 Instant |
|---|---|---|
| LMArena Vision | — | 1254 |
Multilingual Not comparable
Codestral: —, Kimi K2.5 Instant: 52.0 (#94)
| Benchmark | Codestral | Kimi K2.5 Instant |
|---|---|---|
| LMArena Non-English | — | 1406 |
| LMArena Chinese | — | 1449 |
| LMArena French | — | 1403 |
| LMArena German | — | 1413 |
| LMArena Korean | — | 1378 |
| LMArena Russian | — | 1404 |
| LMArena Spanish | — | 1447 |
Instruction Following Not comparable
Codestral: —, Kimi K2.5 Instant: 75.3 (#65)
| Benchmark | Codestral | Kimi K2.5 Instant |
|---|---|---|
| LMArena Instruction Following | — | 1430 |
Long Context Not comparable
Codestral: —, Kimi K2.5 Instant: 43.9 (#83)
| Benchmark | Codestral | Kimi K2.5 Instant |
|---|---|---|
| LMArena Longer Query | — | 1435 |
Writing & Preference Not comparable
Codestral: —, Kimi K2.5 Instant: 60.6 (#95)
| Benchmark | Codestral | Kimi K2.5 Instant |
|---|---|---|
| LMArena Text | — | 1420 |
| LMArena Creative Writing | — | 1381 |
| LMArena Multi-Turn | — | 1427 |
Frequently asked questions
Is Codestral better than Kimi K2.5 Instant?
Kimi K2.5 Instant is the stronger model overall, scoring 43.6 to 30.6 on the Noometry Index.
Is Codestral or Kimi K2.5 Instant better for coding?
Kimi K2.5 Instant scores higher on coding benchmarks: 42.6 versus 27.3 in the Noometry coding category.
How many benchmarks do Codestral and Kimi K2.5 Instant share?
0 benchmarks have published results for both models. Codestral has 7 scored results on Noometry and Kimi K2.5 Instant has 18.