Model comparison
GPT-5.4 mini vs Granite 4.0 H Small
GPT-5.4 mini is the stronger model overall, scoring 44.8 to 35.9 on the Noometry Index.
Last verified . 14 shared benchmarks.
Summary
- They share 14 benchmarks with published results for both. GPT-5.4 mini scores higher in 8 categories and Granite 4.0 H Small in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where GPT-5.4 mini leads 64.2 to 44.0.
- Granite 4.0 H Small has downloadable open weights; the other is API-only.
Side by side
| GPT-5.4 mini | Granite 4.0 H Small | |
|---|---|---|
| Provider | OpenAI | IBM |
| Noometry Index | 44.8 | 35.9 |
| Released | 2026-03-17 | — |
| Weights | Proprietary | Open |
| Context window | 400K | — |
| Max output | 128K | — |
| Input $ / M tokens | $0.75 | — |
| Output $ / M tokens | $4.50 | — |
| Results tracked | 46 | 19 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-5.4 mini leads
GPT-5.4 mini: 45.0 (#67), Granite 4.0 H Small: 35.8 (#207)
| Benchmark | GPT-5.4 mini | Granite 4.0 H Small |
|---|---|---|
| LMArena Coding | 1438 | 1247 |
| FrontierCode | 27% | — |
| LMArena WebDev | 1397 | — |
| SciCode | 49.9% | — |
| WeirdML | 60.3% | — |
| ALE-Bench | 1,189 | — |
Agentic & Tool Use Not comparable
GPT-5.4 mini: 29.6 (#74), Granite 4.0 H Small: —
| Benchmark | GPT-5.4 mini | Granite 4.0 H Small |
|---|---|---|
| DeepResearch Bench | 36.3% | — |
Reasoning GPT-5.4 mini leads
GPT-5.4 mini: 30.3 (#77), Granite 4.0 H Small: 23.4 (#164)
| Benchmark | GPT-5.4 mini | Granite 4.0 H Small |
|---|---|---|
| LMArena Hard Prompts | 1424 | 1240 |
| ARC-AGI-2 | 18.9% | — |
| Kagi LLM Benchmark | 37.9% | — |
| NYT Connections (extended) | 61.8% | — |
| ARC-AGI-1 | 63.7% | — |
| CritPt | 10% | — |
| Chess Puzzles | 24% | — |
| Thematic Generalization | 61.7% | — |
| Mystery Game Puzzles | 11% | — |
| DTBench | 80% | — |
| LMCA | 40.8% | — |
| Epoch Capabilities Index | 148.83 | — |
| ForecastBench | 57 | — |
Math GPT-5.4 mini leads
GPT-5.4 mini: 45.4 (#63), Granite 4.0 H Small: 29.3 (#219)
| Benchmark | GPT-5.4 mini | Granite 4.0 H Small |
|---|---|---|
| LMArena Math | 1418 | 1251 |
| FrontierMath (Tiers 1-3) | 51.2% | — |
| FrontierMath Tier 4 | 9.8% | — |
| OTIS Mock AIME 2024-2025 | 88.9% | — |
| ProofBench | 21% | — |
| Omni-MATH | — | 29.6% |
| FrontierMath (Feb 2025 set) | 28.3% | — |
| FrontierMath Tier 4 (v1) | 2.1% | — |
Knowledge GPT-5.4 mini leads
GPT-5.4 mini: 51.4 (#62), Granite 4.0 H Small: 31.5 (#210)
| Benchmark | GPT-5.4 mini | Granite 4.0 H Small |
|---|---|---|
| Vectara Hallucination Rate | 5.5% | 5.2% |
| LMArena Expert | 1434 | 1244 |
| GPQA Diamond | 86.9% | — |
| SimpleQA Verified | 29.4% | — |
| MMLU-Pro | — | 56.9% |
| GPQA (HELM) | — | 38.3% |
Multimodal Not comparable
GPT-5.4 mini: 39.0 (#51), Granite 4.0 H Small: —
| Benchmark | GPT-5.4 mini | Granite 4.0 H Small |
|---|---|---|
| LMArena Vision | 1245 | — |
Multilingual GPT-5.4 mini leads
GPT-5.4 mini: 52.1 (#94), Granite 4.0 H Small: 38.7 (#223)
| Benchmark | GPT-5.4 mini | Granite 4.0 H Small |
|---|---|---|
| LMArena Non-English | 1405 | 1216 |
| LMArena Chinese | 1446 | 1250 |
| LMArena Russian | 1417 | 1198 |
| LMArena Spanish | 1403 | 1258 |
| LMArena French | 1440 | — |
| LMArena German | 1407 | — |
| LMArena Japanese | 1375 | — |
| LMArena Korean | 1369 | — |
Instruction Following GPT-5.4 mini leads
GPT-5.4 mini: 74.3 (#99), Granite 4.0 H Small: 68.9 (#178)
| Benchmark | GPT-5.4 mini | Granite 4.0 H Small |
|---|---|---|
| LMArena Instruction Following | 1405 | 1221 |
| IFEval | — | 89% |
Long Context GPT-5.4 mini leads
GPT-5.4 mini: 42.9 (#107), Granite 4.0 H Small: 37.6 (#209)
| Benchmark | GPT-5.4 mini | Granite 4.0 H Small |
|---|---|---|
| LMArena Longer Query | 1407 | 1240 |
Writing & Preference GPT-5.4 mini leads
GPT-5.4 mini: 64.2 (#56), Granite 4.0 H Small: 44.0 (#222)
| Benchmark | GPT-5.4 mini | Granite 4.0 H Small |
|---|---|---|
| LMArena Text | 1411 | 1241 |
| LMArena Creative Writing | 1370 | 1210 |
| LMArena Multi-Turn | 1429 | 1243 |
| EQ-Bench Creative Writing | 1665 | — |
| WildBench | — | 73.9% |
Frequently asked questions
Is GPT-5.4 mini better than Granite 4.0 H Small?
GPT-5.4 mini is the stronger model overall, scoring 44.8 to 35.9 on the Noometry Index.
Is GPT-5.4 mini or Granite 4.0 H Small better for coding?
GPT-5.4 mini scores higher on coding benchmarks: 45.0 versus 35.8 in the Noometry coding category.
How many benchmarks do GPT-5.4 mini and Granite 4.0 H Small share?
14 benchmarks have published results for both models. GPT-5.4 mini has 46 scored results on Noometry and Granite 4.0 H Small has 19.