Model comparison
Devstral Small 2505 vs Olmo 3 32b Think
Olmo 3 32b Think is the stronger model overall, scoring 38.1 to 33.9 on the Noometry Index.
Last verified . 0 shared benchmarks.
Mistral AI
Allen Institute for AI (Ai2)Summary
- The widest gap is in reasoning, where Olmo 3 32b Think leads 24.9 to 19.1.
Side by side
| Devstral Small 2505 | Olmo 3 32b Think | |
|---|---|---|
| Provider | Mistral AI | Allen Institute for AI (Ai2) |
| Noometry Index | 33.9 | 38.1 |
| Released | 2025-05-07 | — |
| Weights | Open | Open |
| Context window | 128K | — |
| Max output | 128K | — |
| Input $ / M tokens | $0.10 | — |
| Output $ / M tokens | $0.30 | — |
| Results tracked | 4 | 14 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Devstral Small 2505: 38.6 (#160), Olmo 3 32b Think: 38.0 (#169)
| Benchmark | Devstral Small 2505 | Olmo 3 32b Think |
|---|---|---|
| SWE-bench Verified (bash only) | 56.4% | — |
| SciCode | 28.8% | — |
| LMArena Coding | — | 1318 |
Reasoning Olmo 3 32b Think leads
Devstral Small 2505: 19.1 (#243), Olmo 3 32b Think: 24.9 (#138)
| Benchmark | Devstral Small 2505 | Olmo 3 32b Think |
|---|---|---|
| Kagi LLM Benchmark | 37.7% | — |
| CritPt | 0% | — |
| LMArena Hard Prompts | — | 1302 |
Math Not comparable
Devstral Small 2505: —, Olmo 3 32b Think: 33.8 (#165)
| Benchmark | Devstral Small 2505 | Olmo 3 32b Think |
|---|---|---|
| LMArena Math | — | 1315 |
Knowledge Not comparable
Devstral Small 2505: —, Olmo 3 32b Think: 34.4 (#189)
| Benchmark | Devstral Small 2505 | Olmo 3 32b Think |
|---|---|---|
| LMArena Expert | — | 1272 |
Multilingual Not comparable
Devstral Small 2505: —, Olmo 3 32b Think: 41.4 (#205)
| Benchmark | Devstral Small 2505 | Olmo 3 32b Think |
|---|---|---|
| LMArena Non-English | — | 1255 |
| LMArena Chinese | — | 1300 |
| LMArena French | — | 1291 |
| LMArena German | — | 1290 |
| LMArena Russian | — | 1255 |
Instruction Following Not comparable
Devstral Small 2505: —, Olmo 3 32b Think: 67.4 (#193)
| Benchmark | Devstral Small 2505 | Olmo 3 32b Think |
|---|---|---|
| LMArena Instruction Following | — | 1275 |
Long Context Not comparable
Devstral Small 2505: —, Olmo 3 32b Think: 39.4 (#177)
| Benchmark | Devstral Small 2505 | Olmo 3 32b Think |
|---|---|---|
| LMArena Longer Query | — | 1296 |
Writing & Preference Not comparable
Devstral Small 2505: —, Olmo 3 32b Think: 49.2 (#188)
| Benchmark | Devstral Small 2505 | Olmo 3 32b Think |
|---|---|---|
| LMArena Text | — | 1300 |
| LMArena Creative Writing | — | 1256 |
| LMArena Multi-Turn | — | 1289 |
Frequently asked questions
Is Devstral Small 2505 better than Olmo 3 32b Think?
Olmo 3 32b Think is the stronger model overall, scoring 38.1 to 33.9 on the Noometry Index.
Is Devstral Small 2505 or Olmo 3 32b Think better for coding?
They score almost the same on coding (38.6 vs 38.0); test both on your own repository before choosing.
How many benchmarks do Devstral Small 2505 and Olmo 3 32b Think share?
0 benchmarks have published results for both models. Devstral Small 2505 has 4 scored results on Noometry and Olmo 3 32b Think has 14.