Model comparison
gpt-oss-120b vs Inkling-Small
Inkling-Small is the stronger model overall, scoring 46.5 to 36.0 on the Noometry Index. gpt-oss-120b costs 9.1× less per token, which makes it the better buy when Inkling-Small's lead doesn't matter for your workload.
Last verified . 25 shared benchmarks.
Summary
- They share 25 benchmarks with published results for both. gpt-oss-120b scores higher in 1 category and Inkling-Small in 7 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Inkling-Small leads 39.0 to 19.5.
- The biggest single-benchmark swing is GPQA Diamond: 75.8% for gpt-oss-120b and 88.5% for Inkling-Small.
- gpt-oss-120b is cheaper at $0.037 / $0.17 per million input/output tokens, against $0.45 / $1.20 for Inkling-Small.
- Inkling-Small accepts more context: 524K tokens versus 131K.
Side by side
| gpt-oss-120b | Inkling-Small | |
|---|---|---|
| Provider | OpenAI | Thinking Machines Lab |
| Noometry Index | 36.0 | 46.5 |
| Released | 2025-08-05 | 2026-07-15 |
| Weights | Open | Open |
| Context window | 131K | 524K |
| Max output | 41K | 1.05M |
| Input $ / M tokens | $0.037 | $0.45 |
| Output $ / M tokens | $0.17 | $1.20 |
| Results tracked | 48 | 33 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Inkling-Small leads
gpt-oss-120b: 33.2 (#251), Inkling-Small: 43.3 (#80)
| Benchmark | gpt-oss-120b | Inkling-Small |
|---|---|---|
| SciCode | 36% | 48.7% |
| LMArena Coding | 1380 | 1451 |
| SWE-bench Verified (bash only) | 26% | — |
| Aider Polyglot | 41.8% | — |
| LMArena WebDev | — | 1408 |
| WeirdML | 48.2% | — |
| ALE-Bench | 575.62 | — |
| AlgoTune | 1.41 | — |
Agentic & Tool Use Not comparable
gpt-oss-120b: 12.1 (#145), Inkling-Small: —
| Benchmark | gpt-oss-120b | Inkling-Small |
|---|---|---|
| Terminal-Bench | 18.7% | — |
| APEX-Agents | 4.4% | — |
| METR Time Horizons | 56.6% | — |
| Vending-Bench 2 | -21.53 | — |
Reasoning Inkling-Small leads
gpt-oss-120b: 19.5 (#236), Inkling-Small: 39.0 (#53)
| Benchmark | gpt-oss-120b | Inkling-Small |
|---|---|---|
| CritPt | 1.1% | 8.3% |
| Chess Puzzles | 20% | 18% |
| LMArena Hard Prompts | 1364 | 1424 |
| Mystery Game Puzzles | 2% | 6% |
| Epoch Capabilities Index | 139.94 | 150.13 |
| ARC-AGI-2 | — | 40.1% |
| SimpleBench | 22.1% | — |
| Kagi LLM Benchmark | 58.6% | — |
| ARC-AGI-1 | — | 84% |
| DTBench | 76.3% | — |
| LMCA | 22.1% | — |
| Surface Evolver Bench | 25% | — |
Math gpt-oss-120b leads
gpt-oss-120b: 50.6 (#43), Inkling-Small: 44.9 (#65)
| Benchmark | gpt-oss-120b | Inkling-Small |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 88.9% | 90% |
| LMArena Math | 1388 | 1453 |
| FrontierMath (Tiers 1-3) | — | 46.3% |
| FrontierMath Tier 4 | — | 17.1% |
| ProofBench | — | 6% |
| Omni-MATH | 68.8% | — |
Knowledge Inkling-Small leads
gpt-oss-120b: 42.3 (#89), Inkling-Small: 48.3 (#71)
| Benchmark | gpt-oss-120b | Inkling-Small |
|---|---|---|
| GPQA Diamond | 75.8% | 88.5% |
| LMArena Expert | 1356 | 1442 |
| SimpleQA Verified | — | 19.1% |
| MMLU-Pro | 79.5% | — |
| Confabulations | 15.7% | — |
| Vectara Hallucination Rate | 14.2% | — |
| GPQA (HELM) | 68.4% | — |
Multimodal Not comparable
gpt-oss-120b: —, Inkling-Small: 38.4 (#59)
| Benchmark | gpt-oss-120b | Inkling-Small |
|---|---|---|
| LMArena Vision | — | 1235 |
Multilingual Inkling-Small leads
gpt-oss-120b: 48.2 (#142), Inkling-Small: 51.7 (#102)
| Benchmark | gpt-oss-120b | Inkling-Small |
|---|---|---|
| LMArena Non-English | 1350 | 1400 |
| LMArena Chinese | 1384 | 1458 |
| LMArena French | 1370 | 1438 |
| LMArena German | 1355 | 1412 |
| LMArena Japanese | 1332 | 1399 |
| LMArena Korean | 1283 | 1355 |
| LMArena Russian | 1343 | 1392 |
| LMArena Spanish | 1388 | 1426 |
Instruction Following Inkling-Small leads
gpt-oss-120b: 69.5 (#168), Inkling-Small: 73.9 (#112)
| Benchmark | gpt-oss-120b | Inkling-Small |
|---|---|---|
| LMArena Instruction Following | 1318 | 1397 |
| IFEval | 83.6% | — |
Long Context Inkling-Small leads
gpt-oss-120b: 31.4 (#273), Inkling-Small: 42.7 (#113)
| Benchmark | gpt-oss-120b | Inkling-Small |
|---|---|---|
| LMArena Longer Query | 1319 | 1401 |
| Fiction.LiveBench | 44.4% | — |
Writing & Preference Inkling-Small leads
gpt-oss-120b: 46.7 (#213), Inkling-Small: 59.8 (#102)
| Benchmark | gpt-oss-120b | Inkling-Small |
|---|---|---|
| LMArena Text | 1366 | 1413 |
| LMArena Creative Writing | 1274 | 1330 |
| EQ-Bench Creative Writing | 961 | 1491 |
| LMArena Multi-Turn | 1340 | 1420 |
| Short-Story Creative Writing | 77.1% | — |
| WildBench | 84.5% | — |
Frequently asked questions
Is gpt-oss-120b better than Inkling-Small?
Inkling-Small is the stronger model overall, scoring 46.5 to 36.0 on the Noometry Index. gpt-oss-120b costs 9.1× less per token, which makes it the better buy when Inkling-Small's lead doesn't matter for your workload.
Which is cheaper, gpt-oss-120b or Inkling-Small?
gpt-oss-120b is cheaper. It lists at $0.037 per million input tokens and $0.17 per million output tokens; Inkling-Small lists at $0.45 and $1.20.
Is gpt-oss-120b or Inkling-Small better for coding?
Inkling-Small scores higher on coding benchmarks: 43.3 versus 33.2 in the Noometry coding category.
Which has the bigger context window?
Inkling-Small does, with 524K tokens against 131K.
How many benchmarks do gpt-oss-120b and Inkling-Small share?
25 benchmarks have published results for both models. gpt-oss-120b has 48 scored results on Noometry and Inkling-Small has 33.