Model comparison
GPT-5 Mini vs Granite 4.2 30b
GPT-5 Mini and Granite 4.2 30b score almost the same on the Noometry Index (41.8 vs 41.8), so choose on price, context window or the category you care about most.
Last verified . 11 shared benchmarks.
Summary
- They share 11 benchmarks with published results for both. GPT-5 Mini scores higher in 5 categories and Granite 4.2 30b in 2 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where GPT-5 Mini leads 45.6 to 39.1.
- Granite 4.2 30b has downloadable open weights; the other is API-only.
Side by side
| GPT-5 Mini | Granite 4.2 30b | |
|---|---|---|
| Provider | OpenAI | IBM |
| Noometry Index | 41.8 | 41.8 |
| Released | 2025-08-07 | — |
| Weights | Proprietary | Open |
| Context window | 400K | — |
| Max output | 128K | — |
| Input $ / M tokens | $0.25 | — |
| Output $ / M tokens | $2 | — |
| Results tracked | 60 | 11 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
GPT-5 Mini: 40.1 (#146), Granite 4.2 30b: 41.0 (#126)
| Benchmark | GPT-5 Mini | Granite 4.2 30b |
|---|---|---|
| LMArena Coding | 1406 | 1396 |
| SWE-bench Verified | 64.7% | — |
| SWE-bench Verified (bash only) | 59.8% | — |
| SWE-bench Multilingual | 39.7% | — |
| SciCode | 39.2% | — |
| WeirdML | 52.7% | — |
| ALE-Bench | 799.77 | — |
| AlgoTune | 1.38 | — |
Agentic & Tool Use Not comparable
GPT-5 Mini: 31.1 (#70), Granite 4.2 30b: —
| Benchmark | GPT-5 Mini | Granite 4.2 30b |
|---|---|---|
| Terminal-Bench | 34.8% | — |
| Berkeley Function Calling Leaderboard | 55.5% | — |
| Vending-Bench 2 | -31.18 | — |
Reasoning Granite 4.2 30b leads
GPT-5 Mini: 23.9 (#168), Granite 4.2 30b: 27.8 (#112)
| Benchmark | GPT-5 Mini | Granite 4.2 30b |
|---|---|---|
| LMArena Hard Prompts | 1380 | 1374 |
| ARC-AGI-2 | 4.4% | — |
| Kagi LLM Benchmark | 70.3% | — |
| ARC-AGI-1 | 54.3% | — |
| CritPt | 0% | — |
| Chess Puzzles | 30% | — |
| EnigmaEval | 8.2% | — |
| Mystery Game Puzzles | 10% | — |
| DTBench | 80.5% | — |
| LMCA | 34.2% | — |
| Epoch Capabilities Index | 145.52 | — |
| ForecastBench | 61 | — |
Math Not comparable
GPT-5 Mini: 46.7 (#69), Granite 4.2 30b: —
| Benchmark | GPT-5 Mini | Granite 4.2 30b |
|---|---|---|
| FrontierMath (Tiers 1-3) | 46.7% | — |
| FrontierMath Tier 4 | 12.2% | — |
| OTIS Mock AIME 2024-2025 | 86.7% | — |
| ProofBench | 9% | — |
| Omni-MATH | 72.2% | — |
| LMArena Math | 1378 | — |
| MATH Level 5 | 97.8% | — |
| FrontierMath (Feb 2025 set) | 27.2% | — |
| FrontierMath Tier 4 (v1) | 6.3% | — |
Knowledge GPT-5 Mini leads
GPT-5 Mini: 45.6 (#86), Granite 4.2 30b: 39.1 (#138)
| Benchmark | GPT-5 Mini | Granite 4.2 30b |
|---|---|---|
| LMArena Expert | 1379 | 1406 |
| GPQA Diamond | 75% | — |
| Humanity's Last Exam | 19.4% | — |
| SimpleQA Verified | 21.6% | — |
| MMLU-Pro | 83.5% | — |
| Confabulations | 13.3% | — |
| Vectara Hallucination Rate | 12.9% | — |
| GPQA (HELM) | 75.6% | — |
Multimodal Not comparable
GPT-5 Mini: 35.6 (#85), Granite 4.2 30b: —
| Benchmark | GPT-5 Mini | Granite 4.2 30b |
|---|---|---|
| LMArena Vision | 1202 | — |
| VPCT | 40.2% | — |
Multilingual GPT-5 Mini leads
GPT-5 Mini: 48.9 (#137), Granite 4.2 30b: 47.3 (#151)
| Benchmark | GPT-5 Mini | Granite 4.2 30b |
|---|---|---|
| LMArena Non-English | 1363 | 1340 |
| LMArena Chinese | 1385 | 1414 |
| LMArena Russian | 1362 | 1343 |
| LMArena French | 1386 | — |
| LMArena German | 1366 | — |
| LMArena Japanese | 1341 | — |
| LMArena Korean | 1308 | — |
| LMArena Spanish | 1355 | — |
Instruction Following GPT-5 Mini leads
GPT-5 Mini: 76.2 (#46), Granite 4.2 30b: 71.2 (#155)
| Benchmark | GPT-5 Mini | Granite 4.2 30b |
|---|---|---|
| LMArena Instruction Following | 1357 | 1347 |
| IFEval | 92.7% | — |
Long Context Too close to call
GPT-5 Mini: 41.9 (#132), Granite 4.2 30b: 41.4 (#140)
| Benchmark | GPT-5 Mini | Granite 4.2 30b |
|---|---|---|
| LMArena Longer Query | 1355 | 1359 |
| Fiction.LiveBench | 69.4% | — |
Writing & Preference GPT-5 Mini leads
GPT-5 Mini: 55.2 (#148), Granite 4.2 30b: 53.8 (#156)
| Benchmark | GPT-5 Mini | Granite 4.2 30b |
|---|---|---|
| LMArena Text | 1373 | 1361 |
| LMArena Creative Writing | 1325 | 1288 |
| LMArena Multi-Turn | 1363 | 1339 |
| Short-Story Creative Writing | 83.1% | — |
| EQ-Bench Creative Writing | 1313 | — |
| WildBench | 85.5% | — |
Frequently asked questions
Is GPT-5 Mini better than Granite 4.2 30b?
GPT-5 Mini and Granite 4.2 30b score almost the same on the Noometry Index (41.8 vs 41.8), so choose on price, context window or the category you care about most.
Is GPT-5 Mini or Granite 4.2 30b better for coding?
They score almost the same on coding (40.1 vs 41.0); test both on your own repository before choosing.
How many benchmarks do GPT-5 Mini and Granite 4.2 30b share?
11 benchmarks have published results for both models. GPT-5 Mini has 60 scored results on Noometry and Granite 4.2 30b has 11.