Model comparison
gpt-oss-120b vs Granite 4.2 8B
Granite 4.2 8B is the stronger model overall, scoring 40.0 to 36.0 on the Noometry Index. gpt-oss-120b costs 1.5× less per token, which makes it the better buy when Granite 4.2 8B's lead doesn't matter for your workload.
Last verified . 11 shared benchmarks.
Summary
- They share 11 benchmarks with published results for both. gpt-oss-120b scores higher in 3 categories and Granite 4.2 8B in 4 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in long context, where Granite 4.2 8B leads 40.2 to 31.4.
- gpt-oss-120b is cheaper at $0.037 / $0.17 per million input/output tokens, against $0.06 / $0.25 for Granite 4.2 8B.
Side by side
| gpt-oss-120b | Granite 4.2 8B | |
|---|---|---|
| Provider | OpenAI | IBM |
| Noometry Index | 36.0 | 40.0 |
| Released | 2025-08-05 | — |
| Weights | Open | Open |
| Context window | 131K | 131K |
| Max output | 41K | 118K |
| Input $ / M tokens | $0.037 | $0.06 |
| Output $ / M tokens | $0.17 | $0.25 |
| Results tracked | 48 | 11 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Granite 4.2 8B leads
gpt-oss-120b: 33.2 (#251), Granite 4.2 8B: 39.9 (#138)
| Benchmark | gpt-oss-120b | Granite 4.2 8B |
|---|---|---|
| LMArena Coding | 1380 | 1379 |
| SWE-bench Verified (bash only) | 26% | — |
| Aider Polyglot | 41.8% | — |
| SciCode | 36% | — |
| WeirdML | 48.2% | — |
| ALE-Bench | 575.62 | — |
| AlgoTune | 1.41 | — |
Agentic & Tool Use Not comparable
gpt-oss-120b: 12.1 (#145), Granite 4.2 8B: —
| Benchmark | gpt-oss-120b | Granite 4.2 8B |
|---|---|---|
| Terminal-Bench | 18.7% | — |
| APEX-Agents | 4.4% | — |
| METR Time Horizons | 56.6% | — |
| Vending-Bench 2 | -21.53 | — |
Reasoning Granite 4.2 8B leads
gpt-oss-120b: 19.5 (#236), Granite 4.2 8B: 25.5 (#130)
| Benchmark | gpt-oss-120b | Granite 4.2 8B |
|---|---|---|
| LMArena Hard Prompts | 1364 | 1327 |
| SimpleBench | 22.1% | — |
| Kagi LLM Benchmark | 58.6% | — |
| CritPt | 1.1% | — |
| Chess Puzzles | 20% | — |
| Mystery Game Puzzles | 2% | — |
| DTBench | 76.3% | — |
| LMCA | 22.1% | — |
| Surface Evolver Bench | 25% | — |
| Epoch Capabilities Index | 139.94 | — |
Math Not comparable
gpt-oss-120b: 50.6 (#43), Granite 4.2 8B: —
| Benchmark | gpt-oss-120b | Granite 4.2 8B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 88.9% | — |
| Omni-MATH | 68.8% | — |
| LMArena Math | 1388 | — |
Knowledge gpt-oss-120b leads
gpt-oss-120b: 42.3 (#89), Granite 4.2 8B: 37.7 (#144)
| Benchmark | gpt-oss-120b | Granite 4.2 8B |
|---|---|---|
| LMArena Expert | 1356 | 1380 |
| GPQA Diamond | 75.8% | — |
| MMLU-Pro | 79.5% | — |
| Confabulations | 15.7% | — |
| Vectara Hallucination Rate | 14.2% | — |
| GPQA (HELM) | 68.4% | — |
Multilingual gpt-oss-120b leads
gpt-oss-120b: 48.2 (#142), Granite 4.2 8B: 44.5 (#173)
| Benchmark | gpt-oss-120b | Granite 4.2 8B |
|---|---|---|
| LMArena Non-English | 1350 | 1299 |
| LMArena Chinese | 1384 | 1361 |
| LMArena Russian | 1343 | 1283 |
| LMArena French | 1370 | — |
| LMArena German | 1355 | — |
| LMArena Japanese | 1332 | — |
| LMArena Korean | 1283 | — |
| LMArena Spanish | 1388 | — |
Instruction Following Too close to call
gpt-oss-120b: 69.5 (#168), Granite 4.2 8B: 68.7 (#183)
| Benchmark | gpt-oss-120b | Granite 4.2 8B |
|---|---|---|
| LMArena Instruction Following | 1318 | 1298 |
| IFEval | 83.6% | — |
Long Context Granite 4.2 8B leads
gpt-oss-120b: 31.4 (#273), Granite 4.2 8B: 40.2 (#154)
| Benchmark | gpt-oss-120b | Granite 4.2 8B |
|---|---|---|
| LMArena Longer Query | 1319 | 1323 |
| Fiction.LiveBench | 44.4% | — |
Writing & Preference Granite 4.2 8B leads
gpt-oss-120b: 46.7 (#213), Granite 4.2 8B: 49.8 (#183)
| Benchmark | gpt-oss-120b | Granite 4.2 8B |
|---|---|---|
| LMArena Text | 1366 | 1319 |
| LMArena Creative Writing | 1274 | 1238 |
| LMArena Multi-Turn | 1340 | 1299 |
| Short-Story Creative Writing | 77.1% | — |
| EQ-Bench Creative Writing | 961 | — |
| WildBench | 84.5% | — |
Frequently asked questions
Is gpt-oss-120b better than Granite 4.2 8B?
Granite 4.2 8B is the stronger model overall, scoring 40.0 to 36.0 on the Noometry Index. gpt-oss-120b costs 1.5× less per token, which makes it the better buy when Granite 4.2 8B's lead doesn't matter for your workload.
Which is cheaper, gpt-oss-120b or Granite 4.2 8B?
gpt-oss-120b is cheaper. It lists at $0.037 per million input tokens and $0.17 per million output tokens; Granite 4.2 8B lists at $0.06 and $0.25.
Is gpt-oss-120b or Granite 4.2 8B better for coding?
Granite 4.2 8B scores higher on coding benchmarks: 39.9 versus 33.2 in the Noometry coding category.
Which has the bigger context window?
Both accept 131K tokens.
How many benchmarks do gpt-oss-120b and Granite 4.2 8B share?
11 benchmarks have published results for both models. gpt-oss-120b has 48 scored results on Noometry and Granite 4.2 8B has 11.