Claude Fable 5.2 vs GPT-6.1 Sol
Wins 5 of 6 areas
Coding · Agents · Reasoning · Facts · Math
Wins 0 of 6 areas
—
Claude Fable 5.2 is the stronger all-rounder.GPT-6.1 Sol is cheaper.
Both rank among the ten best models we track in math.
Scores updated · 24 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.
- ReasoningHard problems that need careful thinking31Claude Fable 5.23 of 4 tests
- MathCompetition and research-level math10Claude Fable 5.21 of 2 tests · 1 tie
- CodingWriting and fixing software10Claude Fable 5.21 of 1 test
- AgentsCarrying out multi-step tasks on its own10Claude Fable 5.21 of 1 test
- FactsGetting facts right instead of making them up10Claude Fable 5.21 of 1 test
- Long documentsFinding answers in very long texts00Even0 each · 1 tie
Coding, agents, facts and long documents 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 75% 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 Fable 5.2 pulls ahead
- Solves new puzzle games it has never seenARC-AGI-3+26.6points ahead
- Very hard expert questions across many subjectsHumanity's Last Exam+21.4points ahead
- Short factual questions, answered correctlySimpleQA Verified+20.1points ahead
Where GPT-6.1 Sol pulls ahead
- Abstract visual puzzles that people can solveARC-AGI-2+1.7points ahead
Every test, side by side
All 24 tests both models report. The winning score is in its model's colour; marks a score checked independently.
ReasoningClaude Fable 5.2
- ARC-AGI-3Claude Fable 5.2 by 26.679.352.7+26.6
- Humanity's Last ExamClaude Fable 5.2 by 21.474.352.9+21.4
- CritPtClaude Fable 5.2 by 3.735.431.7+3.7
- ARC-AGI-2GPT-6.1 Sol by 1.792.594.2+1.7
MathClaude Fable 5.2
- FrontierMath Tiers 1-3 (v2)Claude Fable 5.2 by 1.495.193.7+1.4
- FrontierMath Tier 4tie100100tie
Other results14 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 v2.1 (max effort)Claude Fable 5.2 by 222 rating points18311609+222 rating
- HLE-DiamondClaude Fable 5.2 by 21.480.258.8+21.4
- Terminal-Bench-Science 0.1Claude Fable 5.2 by 15.273.358.1+15.2
- ARC-AGI-3 (Standard harness, max effort)Claude Fable 5.2 by 1365.752.7+13
- Terminal-Bench 4.0Claude Fable 5.2 by 9.467.658.2+9.4
- CritPt v2 HardClaude Fable 5.2 by 776.569.5+7
- GDP (Surge AI)GPT-6.1 Sol by 6.824.231+6.8
- HealthBench Professional length-adjustedClaude Fable 5.2 by 3.567.764.2+3.5
- HealthBench ProfessionalClaude Fable 5.2 by 2.667.765.1+2.6
- ARC-AGI-3 (Provider Adapter harness, max effort)GPT-6.1 Sol by 1.394.996.2+1.3
- HealthBenchClaude Fable 5.2 by 1.159.658.5+1.1
- HealthBench length-adjustedClaude Fable 5.2 by 1.159.658.5+1.1
- ARC-AGI-1Claude Fable 5.2 by 197.596.5+1
- DeepSWE 1.1tie74.375.2tie
Questions people ask
Which is better, Claude Fable 5.2 or GPT-6.1 Sol?
Claude Fable 5.2 wins five of the six areas where both have results: coding, agents, reasoning, facts and math. GPT-6.1 Sol wins none, but costs 75% less. They are level on long documents.
Which is better for coding?
Claude Fable 5.2. It wins the one coding test both models report.
Which is cheaper?
Claude Fable 5.2 costs $8.00 per million input tokens and $40.00 per million output tokens; GPT-6.1 Sol costs $2.00 and $10.00. That makes GPT-6.1 Sol about 75% cheaper for the same work.
How do you compare the two?
We use the 24 benchmark tests both models have published scores on. The verdict counts the 10 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 14 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.