GPT-5.1 vs gpt-oss-120b
Wins 6 of 6 areas
Coding · Agents · Reasoning · Facts · Long documents · Following instructions
Wins 0 of 6 areas
—
GPT-5.1 is the stronger all-rounder.gpt-oss-120b is cheaper.
Scores updated · 33 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.
- ReasoningHard problems that need careful thinking40GPT-5.14 of 4 tests
- FactsGetting facts right instead of making them up40GPT-5.14 of 4 tests
- CodingWriting and fixing software30GPT-5.13 of 3 tests
- AgentsCarrying out multi-step tasks on its own20GPT-5.12 of 2 tests
- Following instructionsDoing exactly what it is asked20GPT-5.12 of 2 tests
- Long documentsFinding answers in very long texts10GPT-5.11 of 1 test
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 tests each model wins by the widest margin, up to three each. Scores are out of 100.
Where GPT-5.1 pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+38.9points ahead
- Short factual questions, answered correctlySimpleQA Verified+34.1points ahead
- Common-sense trick questionsSimpleBench+31.1points ahead
Where gpt-oss-120b pulls ahead
No clear win on a test scored out of 100.
Every test, side by side
All 33 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingGPT-5.1
- Terminal-Bench 2.1GPT-5.1 by 26.252.426.2+26.2
- Terminal-Bench HardGPT-5.1 by 2245.523.5+22
- SciCodeGPT-5.1 by 9.343.334+9.3
AgentsGPT-5.1
- GDPValGPT-5.1 by 10.916.55.6+10.9
- τ-Bench V3 · BankingGPT-5.1 by 3.115.912.8+3.1
ReasoningGPT-5.1
- SimpleBenchGPT-5.1 by 31.153.222.1+31.1
- GPQA DiamondGPT-5.1 by 9.187.378.2+9.1
- Humanity's Last ExamGPT-5.1 by 8.928.519.6+8.9
- CritPtGPT-5.1 by 3.84.91.1+3.8
FactsGPT-5.1
- AA-Omniscience · Non-hallucinationGPT-5.1 by 38.948.19.2+38.9
- SimpleQA VerifiedGPT-5.1 by 34.14813.9+34.1
- AA-Omniscience · AccuracyGPT-5.1 by 15.937.721.8+15.9
- Vectara HHEM hallucination ratelower is betterGPT-5.1 by 2.112.114.2+2.1
Following instructionsGPT-5.1
- Multi-ChallengeGPT-5.1 by 18.163.445.3+18.1
- IFBenchGPT-5.1 by 3.972.969+3.9
Other results17 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.
- AA-OmniscienceGPT-5.1 by 54.65.4-49.3+54.6
- Artificial Analysis Coding IndexGPT-5.1 by 1949.430.4+19
- τ²-Bench Telecom (AA run)GPT-5.1 by 16.181.965.8+16.1
- AA Agentic IndexGPT-5.1 by 15.421.66.2+15.4
- AA IntelligenceGPT-5.1 by 13.124.711.6+13.1
- vectara_avg_summary_lengthGPT-5.1 by 119.2 rating points254.4135.2+119.2 rating
- bbqgpt-oss-120b by 9.888.798.5+9.8
- XSTestGPT-5.1 by 5.598.292.7+5.5
- AIME 2025GPT-5.1 by 49490+4
- HarmBenchgpt-oss-120b by 2.497.6100+2.4
- vectara_factual_consistencyGPT-5.1 by 2.187.985.8+2.1
- AIR-Bench 2024gpt-oss-120b by 1.886.288+1.8
- HMMT Nov. 2025GPT-5.1 by 1.791.790+1.7
- HMMT Feb. 2025tie96.396.7tie
- simple_safety_teststie99.8100tie
- vectara_answer_ratetie10099.9tie
- anthropic_red_teamtie99.599.5tie
Questions people ask
Which is better, GPT-5.1 or gpt-oss-120b?
GPT-5.1 wins all six areas where both have results: coding, agents, reasoning, facts, long documents and following instructions. gpt-oss-120b wins none, but costs 93% less.
Which is better for coding?
GPT-5.1. It wins 3 of the 3 coding tests both models report; gpt-oss-120b wins none.
Which is cheaper?
GPT-5.1 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 33 benchmark tests both models have published scores on. The verdict counts the 16 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 17 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.