GPT-5 vs gpt-oss-20b
Wins 6 of 6 areas
Coding · Agents · Reasoning · Facts · Long documents · Following instructions
Wins 0 of 6 areas
—
GPT-5 is the stronger all-rounder.gpt-oss-20b is cheaper.
Scores updated · 32 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.
- CodingWriting and fixing software60GPT-56 of 6 tests
- AgentsCarrying out multi-step tasks on its own30GPT-53 of 3 tests
- ReasoningHard problems that need careful thinking30GPT-53 of 3 tests
- FactsGetting facts right instead of making them up20GPT-52 of 2 tests
- Long documentsFinding answers in very long texts10GPT-51 of 1 test
- Following instructionsDoing exactly what it is asked10GPT-51 of 1 test
Long documents and following instructions rest on a single test each.
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-20b costs 98% 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 pulls ahead
- Reasons across sets of long documentsAA-LCR+43.5points ahead
- Finds hard-to-locate facts by browsing the webBrowseComp+26.6points ahead
- Recent programming contest problemsLiveCodeBench v6+26points ahead
Where gpt-oss-20b pulls ahead
No clear win on a test scored out of 100.
Every test, side by side
All 32 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingGPT-5
- LiveCodeBench v6GPT-5 by 268761+26
- SWE-bench VerifiedGPT-5 by 22.574.952.4+22.5
- Terminal-Bench HardGPT-5 by 2232.610.6+22
- Terminal-Bench 2.1GPT-5 by 21.335.213.9+21.3
- SWE-bench MultilingualGPT-5 by 13.455.341.9+13.4
- SciCodeGPT-5 by 442.938.9+4
AgentsGPT-5
- BrowseCompGPT-5 by 26.654.928.3+26.6
- GDPValGPT-5 by 21210+21
- τ-Bench V3 · BankingGPT-5 by 15.122.17+15.1
ReasoningGPT-5
- Humanity's Last ExamGPT-5 by 17.528.511+17.5
- GPQA DiamondGPT-5 by 16.685.468.8+16.6
- CritPtGPT-5 by 4.35.71.4+4.3
FactsGPT-5
- AA-Omniscience · AccuracyGPT-5 by 24.340.316+24.3
- AA-Omniscience · Non-hallucinationGPT-5 by 11.917.85.9+11.9
Other results16 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 by 54.3-8.7-63+54.3
- τ²-BenchGPT-5 by 34.782.447.7+34.7
- HealthBenchGPT-5 by 24.767.242.5+24.7
- τ²-Bench Telecom (AA run)GPT-5 by 24.684.860.2+24.6
- Artificial Analysis Coding IndexGPT-5 by 17.137.820.7+17.1
- GPQA (unspecified)GPT-5 by 14.285.771.5+14.2
- AA IntelligenceGPT-5 by 14239+14
- HMMT Feb. 2025GPT-5 by 11.688.376.7+11.6
- MMLU-ProGPT-5 by 10.787.176.4+10.7
- XSTestGPT-5 by 9.997.187.2+9.9
- AIME 2025GPT-5 by 5.494.689.2+5.4
- AIR-Bench 2024GPT-5 by 1.787.786+1.7
- HarmBenchgpt-oss-20b by 1.197.698.7+1.1
- anthropic_red_teamtie99.199.7tie
- simple_safety_teststie99.8100tie
- bbqtie96.896.7tie
Questions people ask
Which is better, GPT-5 or gpt-oss-20b?
GPT-5 wins all six areas where both have results: coding, agents, reasoning, facts, long documents and following instructions. gpt-oss-20b wins none, but costs 98% less.
Which is better for coding?
GPT-5. It wins 6 of the 6 coding tests both models report; gpt-oss-20b wins none.
Which is cheaper?
GPT-5 costs $1.25 per million input tokens and $10.00 per million output tokens; gpt-oss-20b costs $0.07 and $0.18. That makes gpt-oss-20b about 98% cheaper for the same work.
How do you compare the two?
We use the 32 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 16 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.