Model comparison
GPT-4.1 vs Olmo 2 0325 32b Instruct
GPT-4.1 is the stronger model overall, scoring 35.9 to 32.7 on the Noometry Index.
Last verified . 16 shared benchmarks.
Allen Institute for AI (Ai2)Summary
- They share 16 benchmarks with published results for both. GPT-4.1 scores higher in 5 categories and Olmo 2 0325 32b Instruct in 3 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where GPT-4.1 leads 37.1 to 19.5.
- The biggest single-benchmark swing is MMLU-Pro: 81.1% for GPT-4.1 and 41.4% for Olmo 2 0325 32b Instruct.
- Olmo 2 0325 32b Instruct has downloadable open weights; the other is API-only.
Side by side
| GPT-4.1 | Olmo 2 0325 32b Instruct | |
|---|---|---|
| Provider | OpenAI | Allen Institute for AI (Ai2) |
| Noometry Index | 35.9 | 32.7 |
| Released | 2025-04-14 | — |
| Weights | Proprietary | Open |
| Context window | 1.05M | — |
| Max output | 33K | — |
| Input $ / M tokens | $2 | — |
| Output $ / M tokens | $8 | — |
| Results tracked | 52 | 16 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
GPT-4.1: 34.4 (#238), Olmo 2 0325 32b Instruct: 35.2 (#227)
| Benchmark | GPT-4.1 | Olmo 2 0325 32b Instruct |
|---|---|---|
| LMArena Coding | 1391 | 1210 |
| SWE-bench Verified | 48.5% | — |
| SWE-bench Verified (bash only) | 39.6% | — |
| Aider Polyglot | 52.4% | — |
| WeirdML | 39% | — |
| CadEval | 42% | — |
| ALE-Bench | 558.1 | — |
Agentic & Tool Use Not comparable
GPT-4.1: 34.7 (#43), Olmo 2 0325 32b Instruct: —
| Benchmark | GPT-4.1 | Olmo 2 0325 32b Instruct |
|---|---|---|
| Berkeley Function Calling Leaderboard | 54% | — |
Reasoning Olmo 2 0325 32b Instruct leads
GPT-4.1: 11.7 (#339), Olmo 2 0325 32b Instruct: 23.6 (#175)
| Benchmark | GPT-4.1 | Olmo 2 0325 32b Instruct |
|---|---|---|
| LMArena Hard Prompts | 1384 | 1208 |
| ARC-AGI-2 | 0.4% | — |
| SimpleBench | 27% | — |
| Kagi LLM Benchmark | 52.3% | — |
| ARC-AGI-1 | 5.5% | — |
| Chess Puzzles | 6% | — |
| EnigmaEval | 2.2% | — |
| DTBench | 68.3% | — |
| LMCA | 25.6% | — |
| Epoch Capabilities Index | 136.78 | — |
| ForecastBench | 61.5 | — |
Math Olmo 2 0325 32b Instruct leads
GPT-4.1: 22.3 (#280), Olmo 2 0325 32b Instruct: 26.8 (#255)
| Benchmark | GPT-4.1 | Olmo 2 0325 32b Instruct |
|---|---|---|
| Omni-MATH | 47.1% | 16.1% |
| LMArena Math | 1370 | 1208 |
| FrontierMath (Tiers 1-3) | 6% | — |
| OTIS Mock AIME 2024-2025 | 38.3% | — |
| MATH Level 5 | 83% | — |
| FrontierMath (Feb 2025 set) | 5.5% | — |
| FrontierMath Tier 4 (v1) | 0% | — |
Knowledge GPT-4.1 leads
GPT-4.1: 37.1 (#160), Olmo 2 0325 32b Instruct: 19.5 (#279)
| Benchmark | GPT-4.1 | Olmo 2 0325 32b Instruct |
|---|---|---|
| MMLU-Pro | 81.1% | 41.4% |
| GPQA (HELM) | 65.9% | 28.7% |
| GPQA Diamond | 66.9% | — |
| Humanity's Last Exam | 5.4% | — |
| SimpleQA Verified | 31.1% | — |
| Vectara Hallucination Rate | 5.6% | — |
| LMArena Expert | 1364 | — |
Multimodal Not comparable
GPT-4.1: 38.2 (#67), Olmo 2 0325 32b Instruct: —
| Benchmark | GPT-4.1 | Olmo 2 0325 32b Instruct |
|---|---|---|
| LMArena Vision | 1211 | — |
| GeoBench | 72% | — |
Multilingual GPT-4.1 leads
GPT-4.1: 49.4 (#133), Olmo 2 0325 32b Instruct: 34.8 (#248)
| Benchmark | GPT-4.1 | Olmo 2 0325 32b Instruct |
|---|---|---|
| LMArena Non-English | 1370 | 1160 |
| LMArena Chinese | 1382 | 1192 |
| LMArena Russian | 1377 | 1187 |
| LMArena French | 1382 | — |
| LMArena German | 1381 | — |
| LMArena Japanese | 1319 | — |
| LMArena Korean | 1339 | — |
| LMArena Spanish | 1376 | — |
Instruction Following GPT-4.1 leads
GPT-4.1: 71.3 (#153), Olmo 2 0325 32b Instruct: 61.5 (#244)
| Benchmark | GPT-4.1 | Olmo 2 0325 32b Instruct |
|---|---|---|
| IFEval | 83.8% | 78% |
| LMArena Instruction Following | 1367 | 1186 |
Long Context GPT-4.1 leads
GPT-4.1: 40.0 (#163), Olmo 2 0325 32b Instruct: 36.2 (#234)
| Benchmark | GPT-4.1 | Olmo 2 0325 32b Instruct |
|---|---|---|
| LMArena Longer Query | 1385 | 1194 |
| Fiction.LiveBench | 63.9% | — |
Writing & Preference GPT-4.1 leads
GPT-4.1: 57.6 (#125), Olmo 2 0325 32b Instruct: 42.1 (#236)
| Benchmark | GPT-4.1 | Olmo 2 0325 32b Instruct |
|---|---|---|
| LMArena Text | 1383 | 1218 |
| LMArena Creative Writing | 1363 | 1199 |
| WildBench | 85.4% | 73.4% |
| LMArena Multi-Turn | 1398 | 1221 |
| EQ-Bench Creative Writing | 1420 | — |
Frequently asked questions
Is GPT-4.1 better than Olmo 2 0325 32b Instruct?
GPT-4.1 is the stronger model overall, scoring 35.9 to 32.7 on the Noometry Index.
Is GPT-4.1 or Olmo 2 0325 32b Instruct better for coding?
They score almost the same on coding (34.4 vs 35.2); test both on your own repository before choosing.
How many benchmarks do GPT-4.1 and Olmo 2 0325 32b Instruct share?
16 benchmarks have published results for both models. GPT-4.1 has 52 scored results on Noometry and Olmo 2 0325 32b Instruct has 16.