What are Olmo 3 32B's benchmark scores?

As of 25 Oct 2026, Olmo 3 32B (thinking effort) scores 42.8 ±5.0 on the BenchLeader Index, strongest in instruction following (51) 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 32B rank?

Olmo 3 32B (thinking effort) is #585 of 785 ranked configurations on 25 Oct 2026. 317 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 32B released?

Ai2 released Olmo 3 32B on 20 Nov 2025.

Ai2Open weightsReasoning modelCompare with another model

Olmo 3 32B

Olmo 3 32B is an Ai2 open-weights reasoning model, released 20 Nov 2025. Its best configuration (thinking reasoning effort) ranks #585 of 785 on the BenchLeader Index at 42.8 ±5.0, in the lower half. The ± is the point: 317 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 (51) and lowest in long context (23). Last measured 22 Oct 2026.

Blended price: –
Output speed: –
First answer: –
Context: 66k
Full answer: –
Cost per run: –
Released: 20 Nov 2025

How it scores by categoryDashed line = average model (50). One step of 15 = one standard deviation.

Overall index43
Reasoning43
Coding48
Agents & tools35
Maths48
Knowledge35
Instruction following51
Human preference46
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 32Bthinking	12 Dec 2025	44.0	#552
Olmo 3 32Bthinkingthis page	20 Nov 2025	42.8	#585
Olmo 2 32B	13 Mar 2025	40.0	#665

How its index has moved

9 Sept 2026 to 21 Oct 2026

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.

Reasoning

Benchmark	thinking	Source
Arena Hard Prompts	1326#234	Arena (LMArena)
GPQA Diamond (AA)not in index	61.0%#370	Artificial Analysis
Humanity's Last Exam (AA)not in index	6.4%#389	Artificial Analysis
CritPt	0.0%#315	Artificial Analysis

Coding

Benchmark	thinking	Source	Trend
Arena Coding	1360#232	Arena (LMArena)

Agents & tools

Benchmark	thinking	Source	Trend
Terminal-Bench Hard	1.5%#338	Artificial Analysis
τ²-Bench Telecom (AA)not in index	0.0%#393	Artificial Analysis

Maths

Benchmark	thinking	Source	Trend
Arena Maths	1312#219	Arena (LMArena)

Knowledge

Benchmark	thinking	Source
AA-Omniscience	-58.1#450	Artificial Analysis
AA-Omniscience: accuracynot in index	14.9%#427	Artificial Analysis
AA-Omniscience: non-hallucinationnot in index	14.3%#350	Artificial Analysis

Instruction following

Benchmark	thinking	Source	Trend
IFBench	49.1%#181	Artificial Analysis
Arena Instruction Followingnot in index	1298#240	Arena (LMArena)

Human preference

Benchmark	thinking	Source
Arena Text	1306#249	Arena (LMArena)
Arena Creative Writingnot in index	1265#253	Arena (LMArena)
Arena Multi-turnnot in index	1299#241	Arena (LMArena)
Arena Longer Queriesnot in index	1321#240	Arena (LMArena)

Long context

Benchmark	thinking	Source	Trend
AA-LCR	0.0%#493	Artificial Analysis

Composite

Benchmark	thinking	Source	Trend
AA Intelligence Index v4.3.2	6.5#526	Artificial Analysis

New this month

Questions people ask

What are Olmo 3 32B's benchmark scores?: As of 25 Oct 2026, Olmo 3 32B (thinking effort) scores 42.8 ±5.0 on the BenchLeader Index, strongest in instruction following (51) 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 32B rank?: Olmo 3 32B (thinking effort) is #585 of 785 ranked configurations on 25 Oct 2026. 317 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 32B released?: Ai2 released Olmo 3 32B on 20 Nov 2025.

Data as of 25 Oct 2026. Compare with another model.

Cite as: BenchLeader, “Olmo 3 32B: benchmarks, pricing, speed and rank”, data as of 25 Oct 2026, https://www.benchleader.com/models/olmo-3-32b.