Claude Opus 5.5 vs GPT-6 Sol
Wins 7 of 8 areas
Coding · Agents · Reasoning · Facts · Images and charts · Math · Long documents
Wins 1 of 8 areas
Following instructions
Claude Opus 5.5 is the stronger all-rounder.GPT-6 Sol is cheaper and better at following instructions.
Both rank among the ten best models we track in math.
Scores updated · 38 tests both models report · How we compare
Where each one wins
Tests won in each of the eight areas we test. 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 thinking40Claude Opus 5.54 of 5 tests · 1 tie
- CodingWriting and fixing software40Claude Opus 5.54 of 4 tests
- FactsGetting facts right instead of making them up31Claude Opus 5.53 of 4 tests
- MathCompetition and research-level math20Claude Opus 5.52 of 3 tests · 1 tie
- Images and chartsUnderstanding pictures, charts and video20Claude Opus 5.52 of 2 tests
- AgentsCarrying out multi-step tasks on its own21Claude Opus 5.52 of 3 tests
- Long documentsFinding answers in very long texts10Claude Opus 5.51 of 1 test
- Following instructionsDoing exactly what it is asked01GPT-6 Sol1 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-6 Sol costs 50% 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 Opus 5.5 pulls ahead
- Fixes real GitHub issues, working as an agentLiveBench · Agentic Coding+18.8points ahead
- Real work tasks from 44 professionsGDPVal+17.9points ahead
- Complex command-line tasks across many fieldsTerminal-Bench 4.0+15.7points ahead
Where GPT-6 Sol pulls ahead
- Finds the root cause of IT system incidentsAA IT-Bench SRE+11.2points ahead
- Follows detailed instructions exactlyLiveBench · Instruction Following+2.9points ahead
Every test, side by side
All 38 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingClaude Opus 5.5
- LiveBench · Agentic CodingClaude Opus 5.5 by 18.871.752.9+18.8
- LMArena · WebDevClaude Opus 5.5 by 142 rating points18151673+142 rating
- SciCodeClaude Opus 5.5 by 9.366.957.6+9.3
- LiveBench · CodingClaude Opus 5.5 by 7.589.381.8+7.5
AgentsClaude Opus 5.5
- GDPValClaude Opus 5.5 by 17.968.350.4+17.9
- Terminal-Bench 4.0Claude Opus 5.5 by 15.759.643.9+15.7
- AA IT-Bench SREGPT-6 Sol by 11.238.249.4+11.2
ReasoningClaude Opus 5.5
- SimpleBenchClaude Opus 5.5 by 15.388.473.1+15.3
- Humanity's Last ExamClaude Opus 5.5 by 13.561.447.9+13.5
- LiveBench · ReasoningClaude Opus 5.5 by 3.592.288.7+3.5
- ARC-AGI-2Claude Opus 5.5 by 2.191.789.6+2.1
- CritPttie31.730.9tie
FactsClaude Opus 5.5
- AA-Omniscience · AccuracyClaude Opus 5.5 by 11.766.254.5+11.7
- SimpleQA VerifiedClaude Opus 5.5 by 11.572.260.7+11.5
- Vectara HHEM hallucination ratelower is betterGPT-6 Sol by 3.49.96.5+3.4
- AA-Omniscience · Non-hallucinationClaude Opus 5.5 by 1.541.439.9+1.5
Images and chartsClaude Opus 5.5
- LMArena · VisionClaude Opus 5.5 by 91 rating points13241233+91 rating
- MMMU-ProClaude Opus 5.5 by 4.887.782.9+4.8
MathClaude Opus 5.5
- FrontierMath Tier 4Claude Opus 5.5 by 59590+5
- FrontierMath Tiers 1-3 (v2)Claude Opus 5.5 by 1.491.289.8+1.4
- LiveBench · Mathematicstie97.196.4tie
Following instructionsGPT-6 Sol
- LiveBench · Instruction FollowingGPT-6 Sol by 2.965.768.6+2.9
Other results15 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.
- GDPval-AA 2.1Claude Opus 5.5 by 359 rating points18461487+359 rating
- Terminal-Bench-Science 0.1Claude Opus 5.5 by 31.45927.6+31.4
- AA-OmniscienceClaude Opus 5.5 by 19.346.427.1+19.3
- OSWorld 2.0Claude Opus 5.5 by 17.481.864.4+17.4
- Terminal-Bench 4.0Claude Opus 5.5 by 1766.449.4+17
- vectara_avg_summary_lengthClaude Opus 5.5 by 120.7 rating points192.171.4+120.7 rating
- AA IntelligenceClaude Opus 5.5 by 1057.647.6+10
- DeepSWE 1.1Claude Opus 5.5 by 5.474.268.8+5.4
- HealthBench length-adjustedClaude Opus 5.5 by 3.85753.2+3.8
- vectara_factual_consistencyGPT-6 Sol by 3.490.193.5+3.4
- ARC-AGI-1Claude Opus 5.5 by 297.595.5+2
- livebench_languageClaude Opus 5.5 by 186.385.3+1
- HealthBench Professional length-adjustedtie59.960.8tie
- livebench_data_analysistie80.381.2tie
- vectara_answer_ratetie99.7100tie
Questions people ask
Which is better, Claude Opus 5.5 or GPT-6 Sol?
Claude Opus 5.5 wins seven of the eight areas we test: coding, agents, reasoning, facts, images and charts, math and long documents. GPT-6 Sol wins following instructions, and costs 50% less.
Which is better for coding?
Claude Opus 5.5. It wins 4 of the 4 coding tests both models report; GPT-6 Sol wins none.
Which is cheaper?
Claude Opus 5.5 costs $4.00 per million input tokens and $20.00 per million output tokens; GPT-6 Sol costs $2.00 and $10.00. That makes GPT-6 Sol about 50% cheaper for the same work.
How do you compare the two?
We use the 38 benchmark tests both models have published scores on. The verdict counts the 23 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 15 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.