Claude Opus 4.8 vs GPT-6.1 Sol
Wins 0 of 8 areas
—
Wins 7 of 8 areas
Coding · Agents · Reasoning · Facts · Math · Long documents · Following instructions
GPT-6.1 Sol is the stronger all-rounder.
Scores updated · 34 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 thinking06GPT-6.1 Sol6 of 6 tests
- AgentsCarrying out multi-step tasks on its own03GPT-6.1 Sol3 of 3 tests
- MathCompetition and research-level math03GPT-6.1 Sol3 of 3 tests
- CodingWriting and fixing software12GPT-6.1 Sol2 of 4 tests · 1 tie
- FactsGetting facts right instead of making them up12GPT-6.1 Sol2 of 3 tests
- Long documentsFinding answers in very long texts01GPT-6.1 Sol1 of 1 test
- Following instructionsDoing exactly what it is asked01GPT-6.1 Sol1 of 1 test
- Images and chartsUnderstanding pictures, charts and video00Even0 each · 1 tie
Images and charts, 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-6.1 Sol costs 85% 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-6.1 Sol pulls ahead
- Solves new puzzle games it has never seenARC-AGI-3+51.2points ahead
- Extremely hard research-level math problemsFrontierMath Tier 4+43.9points ahead
- Complex command-line tasks across many fieldsTerminal-Bench 4.0+34.4points ahead
Where Claude Opus 4.8 pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+15points ahead
- Programming problems, refreshed regularlyLiveBench · Coding+1.4points ahead
Every test, side by side
All 34 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingGPT-6.1 Sol
- LMArena · WebDevGPT-6.1 Sol by 193 rating points15561749+193 rating
- LiveBench · Agentic CodingGPT-6.1 Sol by 4.150.554.5+4.1
- LiveBench · CodingClaude Opus 4.8 by 1.481.880.4+1.4
- SciCodetie54.454.2tie
AgentsGPT-6.1 Sol
- Terminal-Bench 4.0GPT-6.1 Sol by 34.421.756.1+34.4
- AA ApexAgentsGPT-6.1 Sol by 20.639.460+20.6
- GDPValGPT-6.1 Sol by 747.754.7+7
ReasoningGPT-6.1 Sol
- ARC-AGI-3GPT-6.1 Sol by 51.21.552.7+51.2
- ARC-AGI-2GPT-6.1 Sol by 22.172.194.2+22.1
- SimpleBenchGPT-6.1 Sol by 18.164.882.9+18.1
- CritPtGPT-6.1 Sol by 10.820.931.7+10.8
- Humanity's Last ExamGPT-6.1 Sol by 4.248.752.9+4.2
- LiveBench · ReasoningGPT-6.1 Sol by 3.489.292.6+3.4
FactsGPT-6.1 Sol
- SimpleQA VerifiedGPT-6.1 Sol by 20.95373.9+20.9
- AA-Omniscience · Non-hallucinationClaude Opus 4.8 by 1560.745.7+15
- AA-Omniscience · AccuracyGPT-6.1 Sol by 13.348.862.1+13.3
MathGPT-6.1 Sol
- FrontierMath Tier 4GPT-6.1 Sol by 43.956.1100+43.9
- FrontierMath Tiers 1-3 (v2)GPT-6.1 Sol by 13.78093.7+13.7
- LiveBench · MathematicsGPT-6.1 Sol by 2.594.396.8+2.5
Following instructionsGPT-6.1 Sol
- LiveBench · Instruction FollowingGPT-6.1 Sol by 2.27274.2+2.2
Other results12 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.
- GDP (Surge AI)Claude Opus 4.8 by 52.884.832+52.8
- Terminal-Bench 4.0GPT-6.1 Sol by 34.623.658.2+34.6
- HiL-Bench (Tools-allowed)GPT-6.1 Sol by 2735.362.3+27
- livebench_data_analysisGPT-6.1 Sol by 16.76682.7+16.7
- DeepSWE 1.1GPT-6.1 Sol by 16.25975.2+16.2
- OSWorld 2.0GPT-6.1 Sol by 15.755.771.4+15.7
- AA-OmniscienceGPT-6.1 Sol by 12.728.841.5+12.7
- livebench_languageGPT-6.1 Sol by 10.479.790.1+10.4
- AA IntelligenceGPT-6.1 Sol by 1041.851.8+10
- HealthBench ProfessionalGPT-6.1 Sol by 8.455.864.2+8.4
- ARC-AGI-1GPT-6.1 Sol by 492.596.5+4
- HealthBenchtie59.358.5tie
Questions people ask
Which is better, Claude Opus 4.8 or GPT-6.1 Sol?
GPT-6.1 Sol wins seven of the eight areas we test: coding, agents, reasoning, facts, math, long documents and following instructions. Claude Opus 4.8 wins none. They are level on images and charts.
Which is better for coding?
GPT-6.1 Sol. It wins 2 of the 4 coding tests both models report; Claude Opus 4.8 wins 1, and 1 is a tie.
Which is cheaper?
Claude Opus 4.8 costs $5.00 per million input tokens and $25.00 per million output tokens; GPT-6.1 Sol costs $2.00 and $2.50. That makes GPT-6.1 Sol about 85% cheaper for the same work.
How do you compare the two?
We use the 34 benchmark tests both models have published scores on. The verdict counts the 22 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 12 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.