Model comparison
GPT-5.4 Pro vs Granite 4.0 H Small
GPT-5.4 Pro is the stronger model overall, scoring 58.8 to 35.9 on the Noometry Index.
Last verified . 1 shared benchmarks.
Summary
- They share 1 benchmark with published results for both. GPT-5.4 Pro scores higher in 4 categories and Granite 4.0 H Small in 0 categories; 4 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where GPT-5.4 Pro leads 71.0 to 23.4.
- Granite 4.0 H Small has downloadable open weights; the other is API-only.
Side by side
| GPT-5.4 Pro | Granite 4.0 H Small | |
|---|---|---|
| Provider | OpenAI | IBM |
| Noometry Index | 58.8 | 35.9 |
| 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 | 19 |
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), Granite 4.0 H Small: 35.8 (#207)
| Benchmark | GPT-5.4 Pro | Granite 4.0 H Small |
|---|---|---|
| WeirdML | 57.4% | — |
| LMArena Coding | — | 1247 |
Reasoning GPT-5.4 Pro leads
GPT-5.4 Pro: 71.0 (#10), Granite 4.0 H Small: 23.4 (#164)
| Benchmark | GPT-5.4 Pro | Granite 4.0 H Small |
|---|---|---|
| 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 | — | 1240 |
| Epoch Capabilities Index | 159.12 | — |
Math GPT-5.4 Pro leads
GPT-5.4 Pro: 72.0 (#17), Granite 4.0 H Small: 29.3 (#219)
| Benchmark | GPT-5.4 Pro | Granite 4.0 H Small |
|---|---|---|
| FrontierMath (Tiers 1-3) | 82.5% | — |
| FrontierMath Tier 4 | 58.5% | — |
| Omni-MATH | — | 29.6% |
| LMArena Math | — | 1251 |
| FrontierMath (Feb 2025 set) | 50% | — |
| FrontierMath Tier 4 (v1) | 37.5% | — |
Knowledge GPT-5.4 Pro leads
GPT-5.4 Pro: 68.3 (#6), Granite 4.0 H Small: 31.5 (#210)
| Benchmark | GPT-5.4 Pro | Granite 4.0 H Small |
|---|---|---|
| Vectara Hallucination Rate | 8.3% | 5.2% |
| GPQA Diamond | 94.6% | — |
| Humanity's Last Exam | 44.3% | — |
| SimpleQA Verified | 46.3% | — |
| MMLU-Pro | — | 56.9% |
| GPQA (HELM) | — | 38.3% |
| LMArena Expert | — | 1244 |
Multilingual Not comparable
GPT-5.4 Pro: —, Granite 4.0 H Small: 38.7 (#223)
| Benchmark | GPT-5.4 Pro | Granite 4.0 H Small |
|---|---|---|
| LMArena Non-English | — | 1216 |
| LMArena Chinese | — | 1250 |
| LMArena Russian | — | 1198 |
| LMArena Spanish | — | 1258 |
Instruction Following Not comparable
GPT-5.4 Pro: —, Granite 4.0 H Small: 68.9 (#178)
| Benchmark | GPT-5.4 Pro | Granite 4.0 H Small |
|---|---|---|
| IFEval | — | 89% |
| LMArena Instruction Following | — | 1221 |
Long Context Not comparable
GPT-5.4 Pro: —, Granite 4.0 H Small: 37.6 (#209)
| Benchmark | GPT-5.4 Pro | Granite 4.0 H Small |
|---|---|---|
| LMArena Longer Query | — | 1240 |
Writing & Preference Not comparable
GPT-5.4 Pro: —, Granite 4.0 H Small: 44.0 (#222)
| Benchmark | GPT-5.4 Pro | Granite 4.0 H Small |
|---|---|---|
| LMArena Text | — | 1241 |
| LMArena Creative Writing | — | 1210 |
| WildBench | — | 73.9% |
| LMArena Multi-Turn | — | 1243 |
Frequently asked questions
Is GPT-5.4 Pro better than Granite 4.0 H Small?
GPT-5.4 Pro is the stronger model overall, scoring 58.8 to 35.9 on the Noometry Index.
Is GPT-5.4 Pro or Granite 4.0 H Small better for coding?
GPT-5.4 Pro scores higher on coding benchmarks: 42.6 versus 35.8 in the Noometry coding category.
How many benchmarks do GPT-5.4 Pro and Granite 4.0 H Small share?
1 benchmark has published results for both models. GPT-5.4 Pro has 16 scored results on Noometry and Granite 4.0 H Small has 19.