Model comparison
Gemini 1.0 Pro vs gpt-oss-20b
gpt-oss-20b is the stronger model overall, scoring 32.5 to 27.3 on the Noometry Index.
Last verified . 19 shared benchmarks.
GoogleSummary
- They share 19 benchmarks with published results for both. Gemini 1.0 Pro scores higher in 1 category and gpt-oss-20b in 7 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in math, where gpt-oss-20b leads 39.4 to 9.3.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 1.1% for Gemini 1.0 Pro and 65.3% for gpt-oss-20b.
- gpt-oss-20b has downloadable open weights; the other is API-only.
Side by side
| Gemini 1.0 Pro | gpt-oss-20b | |
|---|---|---|
| Provider | OpenAI | |
| Noometry Index | 27.3 | 32.5 |
| Released | 2023-12-13 | 2025-08-05 |
| Weights | Proprietary | Open |
| Context window | — | 131K |
| Max output | — | 16K |
| Input $ / M tokens | — | $0.018 |
| Output $ / M tokens | — | $0.09 |
| Results tracked | 24 | 34 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding gpt-oss-20b leads
Gemini 1.0 Pro: 32.2 (#275), gpt-oss-20b: 37.6 (#192)
| Benchmark | Gemini 1.0 Pro | gpt-oss-20b |
|---|---|---|
| LMArena Coding | 1108 | 1306 |
| SciCode | — | 34.4% |
| WeirdML | — | 40.9% |
| ALE-Bench | — | 566.05 |
| HumanEval+ | 55.5% | — |
| MBPP+ | 61.4% | — |
Agentic & Tool Use Not comparable
Gemini 1.0 Pro: —, gpt-oss-20b: 9.3 (#154)
| Benchmark | Gemini 1.0 Pro | gpt-oss-20b |
|---|---|---|
| Terminal-Bench | — | 3.4% |
Reasoning gpt-oss-20b leads
Gemini 1.0 Pro: 17.1 (#296), gpt-oss-20b: 19.3 (#261)
| Benchmark | Gemini 1.0 Pro | gpt-oss-20b |
|---|---|---|
| LMArena Hard Prompts | 1109 | 1274 |
| DTBench | 45.9% | 68% |
| Epoch Capabilities Index | 117.04 | 137.82 |
| Kagi LLM Benchmark | — | 53.2% |
| CritPt | — | 1.4% |
| Chess Puzzles | — | 4% |
| LMCA | — | 14.5% |
Math gpt-oss-20b leads
Gemini 1.0 Pro: 9.3 (#321), gpt-oss-20b: 39.4 (#103)
| Benchmark | Gemini 1.0 Pro | gpt-oss-20b |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 1.1% | 65.3% |
| LMArena Math | 1132 | 1317 |
| Omni-MATH | — | 56.5% |
| MATH Level 5 | 11.2% | — |
Knowledge gpt-oss-20b leads
Gemini 1.0 Pro: 15.6 (#291), gpt-oss-20b: 34.6 (#195)
| Benchmark | Gemini 1.0 Pro | gpt-oss-20b |
|---|---|---|
| GPQA Diamond | 34% | 60.8% |
| LMArena Expert | 1059 | 1258 |
| MMLU-Pro | — | 74% |
| GPQA (HELM) | — | 59.4% |
| MMLU | 70% | — |
Multilingual gpt-oss-20b leads
Gemini 1.0 Pro: 33.4 (#252), gpt-oss-20b: 42.2 (#197)
| Benchmark | Gemini 1.0 Pro | gpt-oss-20b |
|---|---|---|
| LMArena Non-English | 1138 | 1268 |
| LMArena Chinese | 1124 | 1314 |
| LMArena German | 1125 | 1255 |
| LMArena Japanese | 1023 | 1244 |
| LMArena Russian | 1186 | 1278 |
| LMArena Spanish | 1119 | 1267 |
| LMArena French | 1145 | — |
| LMArena Korean | — | 1236 |
Instruction Following gpt-oss-20b leads
Gemini 1.0 Pro: 57.6 (#267), gpt-oss-20b: 61.8 (#240)
| Benchmark | Gemini 1.0 Pro | gpt-oss-20b |
|---|---|---|
| LMArena Instruction Following | 1114 | 1236 |
| IFEval | — | 73.2% |
Long Context gpt-oss-20b leads
Gemini 1.0 Pro: 34.3 (#249), gpt-oss-20b: 37.9 (#209)
| Benchmark | Gemini 1.0 Pro | gpt-oss-20b |
|---|---|---|
| LMArena Longer Query | 1132 | 1250 |
Writing & Preference Too close to call
Gemini 1.0 Pro: 36.0 (#264), gpt-oss-20b: 35.5 (#265)
| Benchmark | Gemini 1.0 Pro | gpt-oss-20b |
|---|---|---|
| LMArena Text | 1149 | 1287 |
| LMArena Creative Writing | 1131 | 1201 |
| LMArena Multi-Turn | 1139 | 1268 |
| EQ-Bench Creative Writing | — | 666 |
| WildBench | — | 73.7% |
Frequently asked questions
Is Gemini 1.0 Pro better than gpt-oss-20b?
gpt-oss-20b is the stronger model overall, scoring 32.5 to 27.3 on the Noometry Index.
Is Gemini 1.0 Pro or gpt-oss-20b better for coding?
gpt-oss-20b scores higher on coding benchmarks: 37.6 versus 32.2 in the Noometry coding category.
How many benchmarks do Gemini 1.0 Pro and gpt-oss-20b share?
19 benchmarks have published results for both models. Gemini 1.0 Pro has 24 scored results on Noometry and gpt-oss-20b has 34.