Model comparison
Claude Haiku 4.5 vs Olmo 3 32b Think
Claude Haiku 4.5 and Olmo 3 32b Think score almost the same on the Noometry Index (39.5 vs 38.7), so choose on price, context window or the category you care about most.
Last verified . 14 shared benchmarks.
Allen Institute for AI (Ai2)Summary
- They share 14 benchmarks with published results for both. Claude Haiku 4.5 scores higher in 7 categories and Olmo 3 32b Think in 1 category; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Olmo 3 32b Think leads 25.9 to 15.1.
- Olmo 3 32b Think has downloadable open weights; the other is API-only.
Side by side
| Claude Haiku 4.5 | Olmo 3 32b Think | |
|---|---|---|
| Provider | Anthropic | Allen Institute for AI (Ai2) |
| Noometry Index | 39.5 | 38.7 |
| Released | 2025-10-15 | — |
| Weights | Proprietary | Open |
| Context window | 200K | — |
| Max output | 64K | — |
| Input $ / M tokens | $1 | — |
| Output $ / M tokens | $5 | — |
| Results tracked | 53 | 14 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude Haiku 4.5 leads
Claude Haiku 4.5: 44.0 (#78), Olmo 3 32b Think: 38.6 (#172)
| Benchmark | Claude Haiku 4.5 | Olmo 3 32b Think |
|---|---|---|
| LMArena Coding | 1453 | 1319 |
| SWE-bench Verified (bash only) | 66.6% | — |
| LMArena WebDev | 1330 | — |
| SWE-bench Multilingual | 64.7% | — |
| SciCode | 43.3% | — |
| WeirdML | 45.4% | — |
| ALE-Bench | 653.48 | — |
Agentic & Tool Use Not comparable
Claude Haiku 4.5: 33.6 (#52), Olmo 3 32b Think: —
| Benchmark | Claude Haiku 4.5 | Olmo 3 32b Think |
|---|---|---|
| Terminal-Bench | 35.5% | — |
| Berkeley Function Calling Leaderboard | 68.7% | — |
| DeepResearch Bench | 45.5% | — |
| BALROG | 31.2% | — |
| ExploitBench | 13.7% | — |
| Vending-Bench 2 | 458.89 | — |
Reasoning Olmo 3 32b Think leads
Claude Haiku 4.5: 15.1 (#320), Olmo 3 32b Think: 25.9 (#140)
| Benchmark | Claude Haiku 4.5 | Olmo 3 32b Think |
|---|---|---|
| LMArena Hard Prompts | 1420 | 1302 |
| ARC-AGI-2 | 4% | — |
| NYT Connections (extended) | 14.3% | — |
| ARC-AGI-1 | 47.7% | — |
| CritPt | 0% | — |
| Chess Puzzles | 8% | — |
| DTBench | 73.6% | — |
| LMCA | 30.9% | — |
| Epoch Capabilities Index | 142.41 | — |
| ForecastBench | 61.4 | — |
Math Claude Haiku 4.5 leads
Claude Haiku 4.5: 44.9 (#78), Olmo 3 32b Think: 36.5 (#165)
| Benchmark | Claude Haiku 4.5 | Olmo 3 32b Think |
|---|---|---|
| LMArena Math | 1396 | 1316 |
| OTIS Mock AIME 2024-2025 | 66.7% | — |
| Omni-MATH | 56.1% | — |
| MATH Level 5 | 96.4% | — |
| FrontierMath (Feb 2025 set) | 5.9% | — |
| FrontierMath Tier 4 (v1) | 2.1% | — |
Knowledge Claude Haiku 4.5 leads
Claude Haiku 4.5: 37.7 (#153), Olmo 3 32b Think: 35.0 (#190)
| Benchmark | Claude Haiku 4.5 | Olmo 3 32b Think |
|---|---|---|
| LMArena Expert | 1442 | 1273 |
| GPQA Diamond | 71.2% | — |
| SimpleQA Verified | 13.2% | — |
| MMLU-Pro | 77.7% | — |
| Vectara Hallucination Rate | 9.8% | — |
| GPQA (HELM) | 60.5% | — |
Multimodal Not comparable
Claude Haiku 4.5: 26.8 (#118), Olmo 3 32b Think: —
| Benchmark | Claude Haiku 4.5 | Olmo 3 32b Think |
|---|---|---|
| Blueprint-Bench 2 | 0% | — |
| LMArena Document | 1420 | — |
Multilingual Claude Haiku 4.5 leads
Claude Haiku 4.5: 49.9 (#129), Olmo 3 32b Think: 41.2 (#210)
| Benchmark | Claude Haiku 4.5 | Olmo 3 32b Think |
|---|---|---|
| LMArena Non-English | 1377 | 1255 |
| LMArena Chinese | 1417 | 1300 |
| LMArena French | 1408 | 1291 |
| LMArena German | 1375 | 1290 |
| LMArena Russian | 1381 | 1254 |
| LMArena Japanese | 1339 | — |
| LMArena Korean | 1347 | — |
| LMArena Spanish | 1420 | — |
Instruction Following Claude Haiku 4.5 leads
Claude Haiku 4.5: 71.4 (#149), Olmo 3 32b Think: 67.2 (#198)
| Benchmark | Claude Haiku 4.5 | Olmo 3 32b Think |
|---|---|---|
| LMArena Instruction Following | 1414 | 1275 |
| IFEval | 80.1% | — |
Long Context Claude Haiku 4.5 leads
Claude Haiku 4.5: 43.6 (#92), Olmo 3 32b Think: 39.4 (#182)
| Benchmark | Claude Haiku 4.5 | Olmo 3 32b Think |
|---|---|---|
| LMArena Longer Query | 1427 | 1296 |
Writing & Preference Claude Haiku 4.5 leads
Claude Haiku 4.5: 57.9 (#123), Olmo 3 32b Think: 49.1 (#193)
| Benchmark | Claude Haiku 4.5 | Olmo 3 32b Think |
|---|---|---|
| LMArena Text | 1396 | 1300 |
| LMArena Creative Writing | 1372 | 1256 |
| LMArena Multi-Turn | 1409 | 1290 |
| WildBench | 83.9% | — |
| EQ-Bench 4 | 1064 | — |
Frequently asked questions
Is Claude Haiku 4.5 better than Olmo 3 32b Think?
Claude Haiku 4.5 and Olmo 3 32b Think score almost the same on the Noometry Index (39.5 vs 38.7), so choose on price, context window or the category you care about most.
Is Claude Haiku 4.5 or Olmo 3 32b Think better for coding?
Claude Haiku 4.5 scores higher on coding benchmarks: 44.0 versus 38.6 in the Noometry coding category.
How many benchmarks do Claude Haiku 4.5 and Olmo 3 32b Think share?
14 benchmarks have published results for both models. Claude Haiku 4.5 has 53 scored results on Noometry and Olmo 3 32b Think has 14.