Model comparison
Olmo 3.1 32b Think vs Qwen2.5 7B Instruct
Olmo 3.1 32b Think is the stronger model overall, scoring 37.9 to 29.0 on the Noometry Index.
Last verified . 0 shared benchmarks.
Allen Institute for AI (Ai2)
Alibaba (Qwen)Summary
- The widest gap is in math, where Olmo 3.1 32b Think leads 36.3 to 12.6.
Side by side
| Olmo 3.1 32b Think | Qwen2.5 7B Instruct | |
|---|---|---|
| Provider | Allen Institute for AI (Ai2) | Alibaba (Qwen) |
| Noometry Index | 37.9 | 29.0 |
| Released | — | 2024-09 |
| Weights | Open | Open |
| Context window | — | 131K |
| Max output | — | 8K |
| Input $ / M tokens | — | $0.17 |
| Output $ / M tokens | — | $0.70 |
| Results tracked | 15 | 15 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Olmo 3.1 32b Think leads
Olmo 3.1 32b Think: 37.7 (#189), Qwen2.5 7B Instruct: 36.5 (#208)
| Benchmark | Olmo 3.1 32b Think | Qwen2.5 7B Instruct |
|---|---|---|
| BigCodeBench Instruct | — | 37.6% |
| LMArena Coding | 1291 | — |
| BigCodeBench Complete | — | 46.1% |
Agentic & Tool Use Not comparable
Olmo 3.1 32b Think: —, Qwen2.5 7B Instruct: 23.8 (#124)
| Benchmark | Olmo 3.1 32b Think | Qwen2.5 7B Instruct |
|---|---|---|
| BALROG | — | 7.8% |
Reasoning Olmo 3.1 32b Think leads
Olmo 3.1 32b Think: 25.2 (#150), Qwen2.5 7B Instruct: 14.8 (#322)
| Benchmark | Olmo 3.1 32b Think | Qwen2.5 7B Instruct |
|---|---|---|
| Chess Puzzles | — | 0% |
| LMArena Hard Prompts | 1272 | — |
| DTBench | — | 47.7% |
| LMCA | — | 6.4% |
| Epoch Capabilities Index | — | 118.51 |
Math Olmo 3.1 32b Think leads
Olmo 3.1 32b Think: 36.3 (#168), Qwen2.5 7B Instruct: 12.6 (#306)
| Benchmark | Olmo 3.1 32b Think | Qwen2.5 7B Instruct |
|---|---|---|
| OTIS Mock AIME 2024-2025 | — | 2.5% |
| Omni-MATH | — | 29.4% |
| LMArena Math | 1305 | — |
Knowledge Olmo 3.1 32b Think leads
Olmo 3.1 32b Think: 35.7 (#181), Qwen2.5 7B Instruct: 17.0 (#286)
| Benchmark | Olmo 3.1 32b Think | Qwen2.5 7B Instruct |
|---|---|---|
| GPQA Diamond | — | 35.5% |
| MMLU-Pro | — | 53.9% |
| GPQA (HELM) | — | 34.1% |
| LMArena Expert | 1295 | — |
| MMLU | — | 72.9% |
Multilingual Not comparable
Olmo 3.1 32b Think: 38.1 (#231), Qwen2.5 7B Instruct: —
| Benchmark | Olmo 3.1 32b Think | Qwen2.5 7B Instruct |
|---|---|---|
| LMArena Non-English | 1209 | — |
| LMArena Chinese | 1242 | — |
| LMArena French | 1260 | — |
| LMArena German | 1262 | — |
| LMArena Russian | 1193 | — |
| LMArena Spanish | 1289 | — |
Instruction Following Olmo 3.1 32b Think leads
Olmo 3.1 32b Think: 65.6 (#218), Qwen2.5 7B Instruct: 63.2 (#231)
| Benchmark | Olmo 3.1 32b Think | Qwen2.5 7B Instruct |
|---|---|---|
| IFEval | — | 74.1% |
| LMArena Instruction Following | 1247 | — |
Long Context Not comparable
Olmo 3.1 32b Think: 38.6 (#195), Qwen2.5 7B Instruct: —
| Benchmark | Olmo 3.1 32b Think | Qwen2.5 7B Instruct |
|---|---|---|
| LMArena Longer Query | 1272 | — |
Writing & Preference Qwen2.5 7B Instruct leads
Olmo 3.1 32b Think: 46.2 (#220), Qwen2.5 7B Instruct: 48.8 (#195)
| Benchmark | Olmo 3.1 32b Think | Qwen2.5 7B Instruct |
|---|---|---|
| LMArena Text | 1272 | — |
| LMArena Creative Writing | 1226 | — |
| WildBench | — | 73.1% |
| LMArena Multi-Turn | 1252 | — |
Frequently asked questions
Is Olmo 3.1 32b Think better than Qwen2.5 7B Instruct?
Olmo 3.1 32b Think is the stronger model overall, scoring 37.9 to 29.0 on the Noometry Index.
Is Olmo 3.1 32b Think or Qwen2.5 7B Instruct better for coding?
Olmo 3.1 32b Think scores higher on coding benchmarks: 37.7 versus 36.5 in the Noometry coding category.
How many benchmarks do Olmo 3.1 32b Think and Qwen2.5 7B Instruct share?
0 benchmarks have published results for both models. Olmo 3.1 32b Think has 15 scored results on Noometry and Qwen2.5 7B Instruct has 15.