Claude Sonnet 4.5 vs gpt-oss-120b
Wins 5 of 6 areas
Coding · Agents · Reasoning · Facts · Long documents
Wins 0 of 6 areas
—
Claude Sonnet 4.5 is the stronger all-rounder.gpt-oss-120b is cheaper.
Scores updated · 37 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 software40Claude Sonnet 4.54 of 4 tests
- FactsGetting facts right instead of making them up40Claude Sonnet 4.54 of 4 tests
- AgentsCarrying out multi-step tasks on its own20Claude Sonnet 4.52 of 3 tests · 1 tie
- ReasoningHard problems that need careful thinking21Claude Sonnet 4.52 of 4 tests · 1 tie
- Long documentsFinding answers in very long texts10Claude Sonnet 4.51 of 1 test
- 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 96% 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 Claude Sonnet 4.5 pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+41.7points ahead
- Common-sense trick questionsSimpleBench+32.2points ahead
- Command-line tasks in a real terminalTerminal-Bench 2.1+29.6points ahead
Where gpt-oss-120b pulls ahead
- Follows unfamiliar, precisely checkable instructionsIFBench+11.7points ahead
- Very hard expert questions across many subjectsHumanity's Last Exam+1.8points ahead
Every test, side by side
All 37 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingClaude Sonnet 4.5
- Terminal-Bench 2.1Claude Sonnet 4.5 by 29.655.826.2+29.6
- SWE-bench ProClaude Sonnet 4.5 by 27.443.616.2+27.4
- Terminal-Bench HardClaude Sonnet 4.5 by 12.135.623.5+12.1
- SciCodeClaude Sonnet 4.5 by 11.745.734+11.7
AgentsClaude Sonnet 4.5
- GDPValClaude Sonnet 4.5 by 14.920.55.6+14.9
- τ-Bench V3 · BankingClaude Sonnet 4.5 by 11.724.512.8+11.7
- Terminal-Bench 4.0tie00tie
ReasoningClaude Sonnet 4.5
- SimpleBenchClaude Sonnet 4.5 by 32.254.322.1+32.2
- GPQA DiamondClaude Sonnet 4.5 by 5.283.478.2+5.2
- Humanity's Last Examgpt-oss-120b by 1.817.819.6+1.8
- CritPttie1.11.1tie
FactsClaude Sonnet 4.5
- AA-Omniscience · Non-hallucinationClaude Sonnet 4.5 by 41.750.99.2+41.7
- SimpleQA VerifiedClaude Sonnet 4.5 by 16.830.713.9+16.8
- AA-Omniscience · AccuracyClaude Sonnet 4.5 by 11.132.921.8+11.1
- Vectara HHEM hallucination ratelower is betterClaude Sonnet 4.5 by 2.21214.2+2.2
Long documentsClaude Sonnet 4.5
- AA-LCRClaude Sonnet 4.5 by 20.372.352+20.3
Following instructionsEven
- IFBenchgpt-oss-120b by 11.757.369+11.7
- Multi-ChallengeClaude Sonnet 4.5 by 1055.345.3+10
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.
- AA-OmniscienceClaude Sonnet 4.5 by 49.1-0.1-49.3+49.1
- HMMT Feb. 2025gpt-oss-120b by 29.267.596.7+29.2
- Artificial Analysis Coding IndexClaude Sonnet 4.5 by 21.752.130.4+21.7
- TAU-bench (retail)Claude Sonnet 4.5 by 18.486.267.8+18.4
- HealthBenchgpt-oss-120b by 13.444.257.6+13.4
- τ²-Bench Telecom (AA run)Claude Sonnet 4.5 by 12.378.165.8+12.3
- AA Agentic IndexClaude Sonnet 4.5 by 11.317.56.2+11.3
- AA IntelligenceClaude Sonnet 4.5 by 9.120.711.6+9.1
- HMMT Nov. 2025gpt-oss-120b by 8.381.790+8.3
- HarmBenchgpt-oss-120b by 892100+8
- vectara_answer_rategpt-oss-120b by 4.395.699.9+4.3
- XSTestClaude Sonnet 4.5 by 3.796.492.7+3.7
- AIME 2025gpt-oss-120b by 38790+3
- vectara_factual_consistencyClaude Sonnet 4.5 by 2.28885.8+2.2
- AIR-Bench 2024Claude Sonnet 4.5 by 1.889.888+1.8
- anthropic_red_teamgpt-oss-120b by 1.398.299.5+1.3
- vectara_avg_summary_lengthtie127.8135.2tie
- bbqtie98.998.5tie
- simple_safety_teststie100100tie
Questions people ask
Which is better, Claude Sonnet 4.5 or gpt-oss-120b?
Claude Sonnet 4.5 wins five of the six areas where both have results: coding, agents, reasoning, facts and long documents. gpt-oss-120b wins none, but costs 96% less. They are level on following instructions.
Which is better for coding?
Claude Sonnet 4.5. It wins 4 of the 4 coding tests both models report; gpt-oss-120b wins none.
Which is cheaper?
Claude Sonnet 4.5 costs $3.00 per million input tokens and $15.00 per million output tokens; gpt-oss-120b costs $0.15 and $0.59. That makes gpt-oss-120b about 96% cheaper for the same work.
How do you compare the two?
We use the 37 benchmark tests both models have published scores on. The verdict counts the 18 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.