Claude Fable 5 vs GPT-6.1 Sol
Wins 2 of 8 areas
Coding · Following instructions
Wins 4 of 8 areas
Agents · Reasoning · Facts · Math
GPT-6.1 Sol wins more areas, narrowly.Claude Fable 5 is better at coding.
Both rank among the ten best models we track in reasoning, facts and math.
Scores updated · 35 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 thinking14GPT-6.1 Sol4 of 5 tests
- AgentsCarrying out multi-step tasks on its own02GPT-6.1 Sol2 of 3 tests · 1 tie
- MathCompetition and research-level math02GPT-6.1 Sol2 of 3 tests · 1 tie
- FactsGetting facts right instead of making them up12GPT-6.1 Sol2 of 3 tests
- CodingWriting and fixing software31Claude Fable 53 of 4 tests
- Following instructionsDoing exactly what it is asked10Claude Fable 51 of 1 test
- Images and chartsUnderstanding pictures, charts and video11Even1 each
- Long documentsFinding answers in very long texts00Even0 each · 1 tie
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 80% less for the same work.
The biggest differences
The three tests each model wins by the widest margin. Scores are out of 100.
Where GPT-6.1 Sol pulls ahead
- Long professional tasks in banking, consulting and lawAA ApexAgents+16.7points ahead
- Complex command-line tasks across many fieldsTerminal-Bench 4.0+13.7points ahead
- Extremely hard research-level math problemsFrontierMath Tier 4+9.8points ahead
Where Claude Fable 5 pulls ahead
- Fixes real GitHub issues, working as an agentLiveBench · Agentic Coding+7.6points ahead
- Code for real scientific research problemsSciCode+6.8points ahead
- Programming problems, refreshed regularlyLiveBench · Coding+5.6points ahead
Every test, side by side
All 35 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingClaude Fable 5
- LMArena · WebDevGPT-6.1 Sol by 125 rating points16241749+125 rating
- LiveBench · Agentic CodingClaude Fable 5 by 7.662.254.5+7.6
- SciCodeClaude Fable 5 by 6.86154.2+6.8
- LiveBench · CodingClaude Fable 5 by 5.68680.4+5.6
AgentsGPT-6.1 Sol
- AA ApexAgentsGPT-6.1 Sol by 16.743.360+16.7
- Terminal-Bench 4.0GPT-6.1 Sol by 13.742.456.1+13.7
- GDPValtie55.554.7tie
ReasoningGPT-6.1 Sol
- ARC-AGI-2GPT-6.1 Sol by 589.294.2+5
- CritPtGPT-6.1 Sol by 3.128.631.7+3.1
- LiveBench · ReasoningGPT-6.1 Sol by 2.989.792.6+2.9
- Humanity's Last ExamClaude Fable 5 by 2.655.552.9+2.6
- SimpleBenchGPT-6.1 Sol by 181.982.9+1
FactsGPT-6.1 Sol
- AA-Omniscience · Non-hallucinationGPT-6.1 Sol by 9.336.445.7+9.3
- AA-Omniscience · AccuracyClaude Fable 5 by 3.365.362.1+3.3
- SimpleQA VerifiedGPT-6.1 Sol by 3.270.773.9+3.2
Images and chartsEven
- LMArena · VisionClaude Fable 5 by 37 rating points13251288+37 rating
- MMMU-ProGPT-6.1 Sol by 1.884.286+1.8
MathGPT-6.1 Sol
- FrontierMath Tier 4GPT-6.1 Sol by 9.890.2100+9.8
- FrontierMath Tiers 1-3 (v2)GPT-6.1 Sol by 6.78793.7+6.7
- LiveBench · Mathematicstie9696.8tie
Following instructionsClaude Fable 5
- LiveBench · Instruction FollowingClaude Fable 5 by 1.675.874.2+1.6
Other results13 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.
- Terminal-Bench-Science 0.1GPT-6.1 Sol by 32.324.757+32.3
- Terminal-Bench 4.0GPT-6.1 Sol by 13.744.558.2+13.7
- HiL-Bench (Tools-allowed)GPT-6.1 Sol by 656.362.3+6
- OSWorld 2.0GPT-6.1 Sol by 5.366.171.4+5.3
- DeepSWE 1.1GPT-6.1 Sol by 5.27075.2+5.2
- HealthBenchClaude Fable 5 by 2.761.258.5+2.7
- AA IntelligenceGPT-6.1 Sol by 2.249.651.8+2.2
- GDP (Surge AI)GPT-6.1 Sol by 2.229.832+2.2
- livebench_data_analysisGPT-6.1 Sol by 2.280.582.7+2.2
- ARC-AGI-1Claude Fable 5 by 298.596.5+2
- AA-OmniscienceClaude Fable 5 by 1.843.341.5+1.8
- HealthBench ProfessionalClaude Fable 5 by 1.86664.2+1.8
- livebench_languagetie90.790.1tie
Questions people ask
Which is better, Claude Fable 5 or GPT-6.1 Sol?
GPT-6.1 Sol wins four of the eight areas we test: agents, reasoning, facts and math. Claude Fable 5 wins coding and following instructions. They are level on images and charts and long documents.
Which is better for coding?
Claude Fable 5. It wins 3 of the 4 coding tests both models report; GPT-6.1 Sol wins 1.
Which is cheaper?
Claude Fable 5 costs $10.00 per million input tokens and $50.00 per million output tokens; GPT-6.1 Sol costs $2.00 and $10.00. That makes GPT-6.1 Sol about 80% cheaper for the same work.
How do you compare the two?
We use the 35 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 13 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.