Model comparison
Devstral Small 2505 vs Kimi K2 (Jul 2025)
Kimi K2 (Jul 2025) is the stronger model overall, scoring 40.9 to 33.9 on the Noometry Index. Devstral Small 2505 costs 6.7× less per token, which makes it the better buy when Kimi K2 (Jul 2025)'s lead doesn't matter for your workload.
Last verified . 2 shared benchmarks.
Mistral AISummary
- They share 2 benchmarks with published results for both. Devstral Small 2505 scores higher in 0 categories and Kimi K2 (Jul 2025) in 2 categories; 2 gaps are clear of the uncertainty.
- The widest gap is in coding, where Kimi K2 (Jul 2025) leads 43.1 to 38.6.
- The biggest single-benchmark swing is Kagi LLM Benchmark: 37.7% for Devstral Small 2505 and 64.4% for Kimi K2 (Jul 2025).
- Devstral Small 2505 is cheaper at $0.10 / $0.30 per million input/output tokens, against $0.57 / $2.30 for Kimi K2 (Jul 2025).
- Kimi K2 (Jul 2025) accepts more context: 262K tokens versus 128K.
Side by side
| Devstral Small 2505 | Kimi K2 (Jul 2025) | |
|---|---|---|
| Provider | Mistral AI | Moonshot AI |
| Noometry Index | 33.9 | 40.9 |
| Released | 2025-05-07 | 2025-07-12 |
| Weights | Open | Open |
| Context window | 128K | 262K |
| Max output | 128K | 262K |
| Input $ / M tokens | $0.10 | $0.57 |
| Output $ / M tokens | $0.30 | $2.30 |
| Results tracked | 4 | 42 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Kimi K2 (Jul 2025) leads
Devstral Small 2505: 38.6 (#160), Kimi K2 (Jul 2025): 43.1 (#83)
| Benchmark | Devstral Small 2505 | Kimi K2 (Jul 2025) |
|---|---|---|
| SWE-bench Verified (bash only) | 56.4% | 63.4% |
| Aider Polyglot | — | 59.1% |
| SciCode | 28.8% | — |
| GSO | — | 4.9% |
| WeirdML | — | 42.8% |
| LMArena Coding | — | 1399 |
| ALE-Bench | — | 597.5 |
Agentic & Tool Use Not comparable
Devstral Small 2505: —, Kimi K2 (Jul 2025): 32.2 (#59)
| Benchmark | Devstral Small 2505 | Kimi K2 (Jul 2025) |
|---|---|---|
| Terminal-Bench | — | 35.7% |
| Berkeley Function Calling Leaderboard | — | 59.1% |
| METR Time Horizons | — | 59.2% |
Reasoning Kimi K2 (Jul 2025) leads
Devstral Small 2505: 19.1 (#243), Kimi K2 (Jul 2025): 22.7 (#173)
| Benchmark | Devstral Small 2505 | Kimi K2 (Jul 2025) |
|---|---|---|
| Kagi LLM Benchmark | 37.7% | 64.4% |
| SimpleBench | — | 26.3% |
| CritPt | 0% | — |
| LMArena Hard Prompts | — | 1384 |
| Epoch Capabilities Index | — | 146.02 |
| ForecastBench | — | 60.2 |
Math Not comparable
Devstral Small 2505: —, Kimi K2 (Jul 2025): 40.1 (#81)
| Benchmark | Devstral Small 2505 | Kimi K2 (Jul 2025) |
|---|---|---|
| Omni-MATH | — | 65.4% |
| LMArena Math | — | 1396 |
| FrontierMath (Feb 2025 set) | — | 21.4% |
| FrontierMath Tier 4 (v1) | — | 0% |
Knowledge Not comparable
Devstral Small 2505: —, Kimi K2 (Jul 2025): 36.9 (#153)
| Benchmark | Devstral Small 2505 | Kimi K2 (Jul 2025) |
|---|---|---|
| MMLU-Pro | — | 81.9% |
| Confabulations | — | 20.4% |
| Vectara Hallucination Rate | — | 17.9% |
| GPQA (HELM) | — | 65.3% |
| LMArena Expert | — | 1363 |
Multilingual Not comparable
Devstral Small 2505: —, Kimi K2 (Jul 2025): 49.8 (#125)
| Benchmark | Devstral Small 2505 | Kimi K2 (Jul 2025) |
|---|---|---|
| LMArena Non-English | — | 1372 |
| LMArena Chinese | — | 1416 |
| LMArena French | — | 1379 |
| LMArena German | — | 1386 |
| LMArena Japanese | — | 1349 |
| LMArena Korean | — | 1324 |
| LMArena Russian | — | 1384 |
| LMArena Spanish | — | 1383 |
Instruction Following Not comparable
Devstral Small 2505: —, Kimi K2 (Jul 2025): 71.3 (#151)
| Benchmark | Devstral Small 2505 | Kimi K2 (Jul 2025) |
|---|---|---|
| IFEval | — | 85% |
| LMArena Instruction Following | — | 1347 |
Long Context Not comparable
Devstral Small 2505: —, Kimi K2 (Jul 2025): 41.2 (#140)
| Benchmark | Devstral Small 2505 | Kimi K2 (Jul 2025) |
|---|---|---|
| Fiction.LiveBench | — | 66.7% |
| CL-bench | — | 17.6% |
| LMArena Longer Query | — | 1353 |
Writing & Preference Not comparable
Devstral Small 2505: —, Kimi K2 (Jul 2025): 62.5 (#76)
| Benchmark | Devstral Small 2505 | Kimi K2 (Jul 2025) |
|---|---|---|
| LMArena Text | — | 1380 |
| LMArena Creative Writing | — | 1349 |
| Short-Story Creative Writing | — | 85.6% |
| EQ-Bench Creative Writing | — | 1666 |
| WildBench | — | 86.2% |
| LMArena Multi-Turn | — | 1371 |
Frequently asked questions
Is Devstral Small 2505 better than Kimi K2 (Jul 2025)?
Kimi K2 (Jul 2025) is the stronger model overall, scoring 40.9 to 33.9 on the Noometry Index. Devstral Small 2505 costs 6.7× less per token, which makes it the better buy when Kimi K2 (Jul 2025)'s lead doesn't matter for your workload.
Which is cheaper, Devstral Small 2505 or Kimi K2 (Jul 2025)?
Devstral Small 2505 is cheaper. It lists at $0.10 per million input tokens and $0.30 per million output tokens; Kimi K2 (Jul 2025) lists at $0.57 and $2.30.
Is Devstral Small 2505 or Kimi K2 (Jul 2025) better for coding?
Kimi K2 (Jul 2025) scores higher on coding benchmarks: 43.1 versus 38.6 in the Noometry coding category.
Which has the bigger context window?
Kimi K2 (Jul 2025) does, with 262K tokens against 128K.
How many benchmarks do Devstral Small 2505 and Kimi K2 (Jul 2025) share?
2 benchmarks have published results for both models. Devstral Small 2505 has 4 scored results on Noometry and Kimi K2 (Jul 2025) has 42.