Ai2Olmo 3.1 32B
Olmo 3.1 32B is an Ai2 open-weights model, released 12 Dec 2025. Its best configuration (thinking reasoning effort) ranks #552 of 785 on the BenchLeader Index at 44.0 ±6.3, in the lower half. The ± is the point: 366 other configurations score within that range, so they and this one cannot be told apart on quality alone — price and speed are what separate them. It scores highest in instruction following (65) and lowest in long context (23). It has been measured at 2 reasoning-effort settings; this summary describes the best-scoring one, and the tabs above switch between them. Last measured 22 Oct 2026.
- Blended price
- –
- Output speed
- –
- First answer
- –
- Context
- 66k
- Full answer
- –
- Cost per run
- –
- Released
- 12 Dec 2025
- Overall index44
- Reasoning42
- Coding45
- Agents & tools34
- Maths47
- Knowledge42
- Instruction following65
- Human preference44
- Long context23
- Composite37
Versions
Ai2 has shipped 3 models under this name. Each is ranked on its own results; a newer version often has fewer results so far, which holds its index nearer the average until more arrive.
| Model | Released | Index | Rank |
|---|---|---|---|
| Olmo 3.1 32Bthinkingthis page | 12 Dec 2025 | 44.0 | #552 |
| Olmo 3 32Bthinking | 20 Nov 2025 | 42.8 | #585 |
| Olmo 2 32B | 13 Mar 2025 | 40.0 | #665 |
Reasoning-effort configurations
The same model behaves differently depending on how much it is allowed to think. Each row is one setting, scored only on the benchmarks that were run at that setting. “Not stated” collects results from publishers that did not say which setting they used; for a reasoning model that is usually its thinking mode, but we do not assume it. Pick a setting here or at the top of the page to see its price, speed and category scores.
| Effort | Index | Rank | Speed | First answer | Chat reply cost | Categories |
|---|---|---|---|---|---|---|
| thinkingbest | 44.0 | #552 | – | – | – | Agents & tools 34 · Coding 45 · Composite 37 · Human preference 44 · Instruction following 65 · Knowledge 42 · Long context 23 · Maths 47 · Reasoning 42 |
| not stated | 42.5 | #592 | – | – | – | Agents & tools 34 · Coding 50 · Composite 37 · Human preference 49 · Instruction following 42 · Knowledge 38 · Long context 23 · Maths 46 · Reasoning 44 |
How its index has moved
9 Sept 2026 to 21 Oct 2026- thinking
- not stated
The index is recomputed from scratch every day, so a line moves when a new benchmark result lands, when a publisher revises a score, or when the models it is normalised against change. Early movement usually means the score is still settling.
Benchmark results
See all LLM benchmarks. One column per reasoning effort. Rank is among every configuration of every model on that benchmark. Hover a score for the run it came from.
Metadata
| Benchmark | thinking | not stated | Source | Trend |
|---|---|---|---|---|
| AA Openness Indexnot in index | 88.9#1 | 88.9#1 | Artificial Analysis |
Reasoning
| Benchmark | thinking | not stated | Source | Trend |
|---|---|---|---|---|
| Arena Hard Prompts | 1305#257 | 1349#216 | Arena (LMArena) | |
| GPQA Diamond (AA)not in index | 59.1%#381 | 53.9%#409 | Artificial Analysis | |
| Humanity's Last Exam (AA)not in index | 6.3%#400 | 5.0%#454 | Artificial Analysis | |
| CritPt | 0.0%#315 | 0.0%#315 | Artificial Analysis |
Coding
| Benchmark | thinking | not stated | Source | Trend |
|---|---|---|---|---|
| Arena Coding | 1341#253 | 1382#215 | Arena (LMArena) |
Agents & tools
| Benchmark | thinking | not stated | Source | Trend |
|---|---|---|---|---|
| Terminal-Bench Hard | 0.0%#362 | 0.0%#362 | Artificial Analysis | |
| τ²-Bench Telecom (AA)not in index | 0.0%#393 | 21.4%#323 | Artificial Analysis |
Maths
| Benchmark | thinking | not stated | Source | Trend |
|---|---|---|---|---|
| Arena Maths | 1303#226 | 1296#230 | Arena (LMArena) |
Knowledge
| Benchmark | thinking | not stated | Source | Trend |
|---|---|---|---|---|
| AA-Omniscience | -43.4#341 | -52.4#408 | Artificial Analysis | |
| AA-Omniscience: accuracynot in index | 13.8%#449 | 12.1%#474 | Artificial Analysis | |
| AA-Omniscience: non-hallucinationnot in index | 33.7%#197 | 26.8%#231 | Artificial Analysis | |
| Global-MMLU-Lite (AA)not in index | 71.5%#30 | – | Artificial Analysis |
Instruction following
| Benchmark | thinking | not stated | Source | Trend |
|---|---|---|---|---|
| IFBench | 66.0%#100 | 39.2%#270 | Artificial Analysis | |
| Arena Instruction Followingnot in index | 1280#259 | 1321#216 | Arena (LMArena) |
Human preference
| Benchmark | thinking | not stated | Source | Trend |
|---|---|---|---|---|
| Arena Text | 1286#268 | 1329#223 | Arena (LMArena) | |
| Arena Creative Writingnot in index | 1248#265 | 1293#222 | Arena (LMArena) | |
| Arena Multi-turnnot in index | 1265#271 | 1330#211 | Arena (LMArena) | |
| Arena Longer Queriesnot in index | 1307#249 | 1337#218 | Arena (LMArena) |
Long context
| Benchmark | thinking | not stated | Source | Trend |
|---|---|---|---|---|
| AA-LCR | 0.0%#493 | 0.0%#493 | Artificial Analysis |
Composite
| Benchmark | thinking | not stated | Source | Trend |
|---|---|---|---|---|
| AA Intelligence Index v4.3.2 | 7.1#492 | 6.5#523 | Artificial Analysis |
See also
Questions people ask
- What are Olmo 3.1 32B's benchmark scores?
- As of 25 Oct 2026, Olmo 3.1 32B (thinking effort) scores 44.0 ±6.3 on the BenchLeader Index, strongest in instruction following (65) and weakest in long context (23). That rests on 10 independent benchmark results, and every score on this page links to its publisher.
- How does Olmo 3.1 32B rank?
- Olmo 3.1 32B (thinking effort) is #552 of 785 ranked configurations on 25 Oct 2026. 366 other configurations score within its margin, so the exact position matters less than the band. The leader is Claude Opus 5.5 (max effort) at 72.6.
- When was Olmo 3.1 32B released?
- Ai2 released Olmo 3.1 32B on 12 Dec 2025. BenchLeader has results for it at 2 reasoning-effort settings.
Data as of 25 Oct 2026. Compare these configurations.
Cite as: BenchLeader, “Olmo 3.1 32B: benchmarks, pricing, speed and rank”, data as of 25 Oct 2026, https://www.benchleader.com/models/olmo-3-1-32b.