Gemini 2.5 Pro vs gpt-oss-120b
Wins 4 of 6 areas
Coding · Reasoning · Facts · Long documents
Wins 1 of 6 areas
Agents
Gemini 2.5 Pro is the stronger all-rounder.gpt-oss-120b is cheaper and better at agents.
Scores updated · 36 tests both models report · How we compare
Where each one wins
Tests won in each of the six areas where both have results. Each piece is one test, so a longer bar means more evidence; grey means the two scored within a point of each other.
- FactsGetting facts right instead of making them up30Gemini 2.5 Pro3 of 4 tests · 1 tie
- CodingWriting and fixing software30Gemini 2.5 Pro3 of 3 tests
- ReasoningHard problems that need careful thinking31Gemini 2.5 Pro3 of 4 tests
- Long documentsFinding answers in very long texts10Gemini 2.5 Pro1 of 1 test
- AgentsCarrying out multi-step tasks on its own02gpt-oss-120b2 of 3 tests · 1 tie
- Following instructionsDoing exactly what it is asked11Even1 each
Long documents rests on a single test.
What it costs
Prices per million tokens, roughly 750,000 words. The bars show the cost of a million tokens read plus a million written.
gpt-oss-120b costs 93% less for the same work.
The biggest differences
The three tests each model wins by the widest margin. Scores are out of 100.
Where Gemini 2.5 Pro pulls ahead
- Short factual questions, answered correctlySimpleQA Verified+42.1points ahead
- Common-sense trick questionsSimpleBench+29.5points ahead
- Answers hard knowledge questions correctlyAA-Omniscience · Accuracy+17.3points ahead
Where gpt-oss-120b pulls ahead
- Follows unfamiliar, precisely checkable instructionsIFBench+20.3points ahead
- Customer-service tasks in a simulated bankτ-Bench V3 · Banking+3.1points ahead
- Very hard expert questions across many subjectsHumanity's Last Exam+1.6points ahead
Every test, side by side
All 36 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingGemini 2.5 Pro
- SciCodeGemini 2.5 Pro by 12.346.334+12.3
- Terminal-Bench HardGemini 2.5 Pro by 326.523.5+3
- Terminal-Bench 2.1Gemini 2.5 Pro by 2.328.526.2+2.3
Agentsgpt-oss-120b
- GDPValgpt-oss-120b by 5.605.6+5.6
- τ-Bench V3 · Bankinggpt-oss-120b by 3.19.712.8+3.1
- Terminal-Bench 4.0tie00tie
ReasoningGemini 2.5 Pro
- SimpleBenchGemini 2.5 Pro by 29.551.622.1+29.5
- GPQA DiamondGemini 2.5 Pro by 5.483.678.2+5.4
- Humanity's Last Examgpt-oss-120b by 1.61819.6+1.6
- CritPtGemini 2.5 Pro by 1.52.61.1+1.5
FactsGemini 2.5 Pro
- SimpleQA VerifiedGemini 2.5 Pro by 42.15613.9+42.1
- AA-Omniscience · AccuracyGemini 2.5 Pro by 17.33921.8+17.3
- Vectara HHEM hallucination ratelower is betterGemini 2.5 Pro by 7.2714.2+7.2
- AA-Omniscience · Non-hallucinationtie9.19.2tie
Following instructionsEven
- IFBenchgpt-oss-120b by 20.348.769+20.3
- Multi-ChallengeGemini 2.5 Pro by 8.353.645.3+8.3
Other results19 tests, not counted
Tests outside the eight areas. They are not counted above: several are summary scores built from other tests, or the same test under another name.
- Aider-PolyglotGemini 2.5 Pro by 34.776.541.8+34.7
- HarmBenchgpt-oss-120b by 34.665.4100+34.6
- AA-OmniscienceGemini 2.5 Pro by 32.9-16.4-49.3+32.9
- Artificial Analysis Coding IndexGemini 2.5 Pro by 16.346.730.4+16.3
- HMMT Feb. 2025gpt-oss-120b by 15.980.896.7+15.9
- AIR-Bench 2024gpt-oss-120b by 14.473.688+14.4
- τ²-Bench Telecom (AA run)gpt-oss-120b by 11.754.165.8+11.7
- HMMT Nov. 2025gpt-oss-120b by 108090+10
- vectara_factual_consistencyGemini 2.5 Pro by 7.29385.8+7.2
- AIME 2025gpt-oss-120b by 78390+7
- XSTestGemini 2.5 Pro by 698.792.7+6
- AA IntelligenceGemini 2.5 Pro by 3.41511.6+3.4
- simple_safety_testsgpt-oss-120b by 397100+3
- vectara_avg_summary_lengthgpt-oss-120b by 28.8 rating points106.4135.2+28.8 rating
- AA Agentic Indexgpt-oss-120b by 2.73.56.2+2.7
- bbqgpt-oss-120b by 2.196.498.5+2.1
- TAU-bench (retail)tie6767.8tie
- vectara_answer_ratetie99.199.9tie
- anthropic_red_teamtie99.599.5tie
Questions people ask
Which is better, Gemini 2.5 Pro or gpt-oss-120b?
Gemini 2.5 Pro wins four of the six areas where both have results: coding, reasoning, facts and long documents. gpt-oss-120b wins agents, and costs 93% less. They are level on following instructions.
Which is better for coding?
Gemini 2.5 Pro. It wins 3 of the 3 coding tests both models report; gpt-oss-120b wins none.
Which is cheaper?
Gemini 2.5 Pro costs $1.25 per million input tokens and $10.00 per million output tokens; gpt-oss-120b costs $0.15 and $0.59. That makes gpt-oss-120b about 93% cheaper for the same work.
How do you compare the two?
We use the 36 benchmark tests both models have published scores on. The verdict counts the 17 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 19 are listed but not counted, because several are summary scores or repeat a test. Each score is the one shown on the model's own page.