Model comparison
GPT-5.4 Pro vs Olmo 2 0325 32b Instruct
GPT-5.4 Pro is the stronger model overall, scoring 58.8 to 32.2 on the Noometry Index.
Last verified . 0 shared benchmarks.
Allen Institute for AI (Ai2)Summary
- The widest gap is in knowledge, where GPT-5.4 Pro leads 68.3 to 19.2.
- Olmo 2 0325 32b Instruct has downloadable open weights; the other is API-only.
Side by side
| GPT-5.4 Pro | Olmo 2 0325 32b Instruct | |
|---|---|---|
| Provider | OpenAI | Allen Institute for AI (Ai2) |
| Noometry Index | 58.8 | 32.2 |
| Released | 2026-03-05 | — |
| Weights | Proprietary | Open |
| Context window | 1.05M | — |
| Max output | 128K | — |
| Input $ / M tokens | $30 | — |
| Output $ / M tokens | $180 | — |
| Results tracked | 16 | 16 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-5.4 Pro leads
GPT-5.4 Pro: 42.6 (#89), Olmo 2 0325 32b Instruct: 34.6 (#222)
| Benchmark | GPT-5.4 Pro | Olmo 2 0325 32b Instruct |
|---|---|---|
| WeirdML | 57.4% | — |
| LMArena Coding | — | 1210 |
Reasoning GPT-5.4 Pro leads
GPT-5.4 Pro: 71.0 (#10), Olmo 2 0325 32b Instruct: 22.6 (#174)
| Benchmark | GPT-5.4 Pro | Olmo 2 0325 32b Instruct |
|---|---|---|
| ARC-AGI-2 | 83.3% | — |
| SimpleBench | 74.1% | — |
| ARC-AGI-1 | 94.5% | — |
| CritPt | 30% | — |
| Chess Puzzles | 58.6% | — |
| EnigmaEval | 23.8% | — |
| LMArena Hard Prompts | — | 1208 |
| Epoch Capabilities Index | 159.12 | — |
Math GPT-5.4 Pro leads
GPT-5.4 Pro: 72.0 (#17), Olmo 2 0325 32b Instruct: 24.8 (#255)
| Benchmark | GPT-5.4 Pro | Olmo 2 0325 32b Instruct |
|---|---|---|
| FrontierMath (Tiers 1-3) | 82.5% | — |
| FrontierMath Tier 4 | 58.5% | — |
| Omni-MATH | — | 16.1% |
| LMArena Math | — | 1208 |
| FrontierMath (Feb 2025 set) | 50% | — |
| FrontierMath Tier 4 (v1) | 37.5% | — |
Knowledge GPT-5.4 Pro leads
GPT-5.4 Pro: 68.3 (#6), Olmo 2 0325 32b Instruct: 19.2 (#274)
| Benchmark | GPT-5.4 Pro | Olmo 2 0325 32b Instruct |
|---|---|---|
| GPQA Diamond | 94.6% | — |
| Humanity's Last Exam | 44.3% | — |
| SimpleQA Verified | 46.3% | — |
| MMLU-Pro | — | 41.4% |
| Vectara Hallucination Rate | 8.3% | — |
| GPQA (HELM) | — | 28.7% |
Multilingual Not comparable
GPT-5.4 Pro: —, Olmo 2 0325 32b Instruct: 35.0 (#243)
| Benchmark | GPT-5.4 Pro | Olmo 2 0325 32b Instruct |
|---|---|---|
| LMArena Non-English | — | 1160 |
| LMArena Chinese | — | 1192 |
| LMArena Russian | — | 1187 |
Instruction Following Not comparable
GPT-5.4 Pro: —, Olmo 2 0325 32b Instruct: 61.8 (#238)
| Benchmark | GPT-5.4 Pro | Olmo 2 0325 32b Instruct |
|---|---|---|
| IFEval | — | 78% |
| LMArena Instruction Following | — | 1186 |
Long Context Not comparable
GPT-5.4 Pro: —, Olmo 2 0325 32b Instruct: 36.2 (#229)
| Benchmark | GPT-5.4 Pro | Olmo 2 0325 32b Instruct |
|---|---|---|
| LMArena Longer Query | — | 1194 |
Writing & Preference Not comparable
GPT-5.4 Pro: —, Olmo 2 0325 32b Instruct: 42.3 (#231)
| Benchmark | GPT-5.4 Pro | Olmo 2 0325 32b Instruct |
|---|---|---|
| LMArena Text | — | 1218 |
| LMArena Creative Writing | — | 1199 |
| WildBench | — | 73.4% |
| LMArena Multi-Turn | — | 1221 |
Frequently asked questions
Is GPT-5.4 Pro better than Olmo 2 0325 32b Instruct?
GPT-5.4 Pro is the stronger model overall, scoring 58.8 to 32.2 on the Noometry Index.
Is GPT-5.4 Pro or Olmo 2 0325 32b Instruct better for coding?
GPT-5.4 Pro scores higher on coding benchmarks: 42.6 versus 34.6 in the Noometry coding category.
How many benchmarks do GPT-5.4 Pro and Olmo 2 0325 32b Instruct share?
0 benchmarks have published results for both models. GPT-5.4 Pro has 16 scored results on Noometry and Olmo 2 0325 32b Instruct has 16.