Model comparison
Claude 3.5 Haiku vs Devstral Small 2505
Devstral Small 2505 is the stronger model overall, scoring 33.9 to 28.9 on the Noometry Index.
Last verified . 2 shared benchmarks.
Mistral AISummary
- They share 2 benchmarks with published results for both. Claude 3.5 Haiku scores higher in 0 categories and Devstral Small 2505 in 2 categories; 2 gaps are clear of the uncertainty.
- The widest gap is in coding, where Devstral Small 2505 leads 38.6 to 32.6.
- Devstral Small 2505 has downloadable open weights; the other is API-only.
Side by side
| Claude 3.5 Haiku | Devstral Small 2505 | |
|---|---|---|
| Provider | Anthropic | Mistral AI |
| Noometry Index | 28.9 | 33.9 |
| Released | 2024-10-22 | 2025-05-07 |
| Weights | Proprietary | Open |
| Context window | — | 128K |
| Max output | — | 128K |
| Input $ / M tokens | — | $0.10 |
| Output $ / M tokens | — | $0.30 |
| Results tracked | 49 | 4 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Devstral Small 2505 leads
Claude 3.5 Haiku: 32.6 (#258), Devstral Small 2505: 38.6 (#160)
| Benchmark | Claude 3.5 Haiku | Devstral Small 2505 |
|---|---|---|
| SciCode | 27.4% | 28.8% |
| SWE-bench Verified (bash only) | — | 56.4% |
| Aider Polyglot | 28% | — |
| WeirdML | 30.7% | — |
| BigCodeBench Instruct | 46.1% | — |
| LiveBench Coding | 51.4% | — |
| LMArena Coding | 1287 | — |
| BigCodeBench Complete | 59% | — |
| CadEval | 32% | — |
Agentic & Tool Use Not comparable
Claude 3.5 Haiku: 27.7 (#90), Devstral Small 2505: —
| Benchmark | Claude 3.5 Haiku | Devstral Small 2505 |
|---|---|---|
| BALROG | 19.3% | — |
Reasoning Devstral Small 2505 leads
Claude 3.5 Haiku: 17.1 (#286), Devstral Small 2505: 19.1 (#243)
| Benchmark | Claude 3.5 Haiku | Devstral Small 2505 |
|---|---|---|
| CritPt | 0% | 0% |
| Kagi LLM Benchmark | — | 37.7% |
| LiveBench Reasoning | 28.1% | — |
| LMArena Hard Prompts | 1251 | — |
| DTBench | 56.7% | — |
| LiveBench Data Analysis | 48.5% | — |
| Epoch Capabilities Index | 127.15 | — |
| LiveBench | 43.5% | — |
Math Not comparable
Claude 3.5 Haiku: 13.7 (#294), Devstral Small 2505: —
| Benchmark | Claude 3.5 Haiku | Devstral Small 2505 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 4.3% | — |
| Omni-MATH | 22.4% | — |
| LiveBench Math | 35.5% | — |
| LMArena Math | 1244 | — |
| MATH Level 5 | 46.4% | — |
| FrontierMath (Feb 2025 set) | 0.3% | — |
Knowledge Not comparable
Claude 3.5 Haiku: 18.7 (#276), Devstral Small 2505: —
| Benchmark | Claude 3.5 Haiku | Devstral Small 2505 |
|---|---|---|
| GPQA Diamond | 38.1% | — |
| MMLU-Pro | 60.5% | — |
| Confabulations | 36.7% | — |
| GPQA (HELM) | 36.3% | — |
| LMArena Expert | 1208 | — |
| MMLU | 74.3% | — |
Multimodal Not comparable
Claude 3.5 Haiku: 26.3 (#113), Devstral Small 2505: —
| Benchmark | Claude 3.5 Haiku | Devstral Small 2505 |
|---|---|---|
| LMArena Vision | 1092 | — |
| GeoBench | 34% | — |
Multilingual Not comparable
Claude 3.5 Haiku: 40.2 (#213), Devstral Small 2505: —
| Benchmark | Claude 3.5 Haiku | Devstral Small 2505 |
|---|---|---|
| LMArena Non-English | 1238 | — |
| LMArena Chinese | 1229 | — |
| LMArena French | 1262 | — |
| LMArena German | 1237 | — |
| LMArena Japanese | 1175 | — |
| LMArena Korean | 1172 | — |
| LMArena Russian | 1253 | — |
| LMArena Spanish | 1261 | — |
Instruction Following Not comparable
Claude 3.5 Haiku: 63.1 (#229), Devstral Small 2505: —
| Benchmark | Claude 3.5 Haiku | Devstral Small 2505 |
|---|---|---|
| LiveBench Instruction Following | 61.9% | — |
| IFEval | 79.2% | — |
| LMArena Instruction Following | 1241 | — |
Long Context Not comparable
Claude 3.5 Haiku: 38.3 (#195), Devstral Small 2505: —
| Benchmark | Claude 3.5 Haiku | Devstral Small 2505 |
|---|---|---|
| LMArena Longer Query | 1261 | — |
Writing & Preference Not comparable
Claude 3.5 Haiku: 42.9 (#228), Devstral Small 2505: —
| Benchmark | Claude 3.5 Haiku | Devstral Small 2505 |
|---|---|---|
| LMArena Text | 1255 | — |
| LMArena Creative Writing | 1233 | — |
| Short-Story Creative Writing | 73.5% | — |
| EQ-Bench Creative Writing | 1146 | — |
| WildBench | 76% | — |
| LMArena Multi-Turn | 1265 | — |
| LiveBench Language | 35.4% | — |
Frequently asked questions
Is Claude 3.5 Haiku better than Devstral Small 2505?
Devstral Small 2505 is the stronger model overall, scoring 33.9 to 28.9 on the Noometry Index.
Is Claude 3.5 Haiku or Devstral Small 2505 better for coding?
Devstral Small 2505 scores higher on coding benchmarks: 38.6 versus 32.6 in the Noometry coding category.
How many benchmarks do Claude 3.5 Haiku and Devstral Small 2505 share?
2 benchmarks have published results for both models. Claude 3.5 Haiku has 49 scored results on Noometry and Devstral Small 2505 has 4.