Claude Fable 5 vs GPT-5 Codex
Wins 6 of 7 areas
Coding · Agents · Reasoning · Facts · Images and charts · Long documents
Wins 1 of 7 areas
Following instructions
Claude Fable 5 is the stronger all-rounder.GPT-5 Codex is cheaper and better at following instructions.
Scores updated · 17 tests both models report · How we compare
Where each one wins
Tests won in each of the seven 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 software30Claude Fable 53 of 3 tests
- ReasoningHard problems that need careful thinking30Claude Fable 53 of 3 tests
- FactsGetting facts right instead of making them up20Claude Fable 52 of 2 tests
- AgentsCarrying out multi-step tasks on its own10Claude Fable 51 of 1 test
- Images and chartsUnderstanding pictures, charts and video10Claude Fable 51 of 1 test
- Long documentsFinding answers in very long texts10Claude Fable 51 of 1 test
- Following instructionsDoing exactly what it is asked01GPT-5 Codex1 of 1 test
Agents, 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-5 Codex costs 81% 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 pulls ahead
- Very hard expert questions across many subjectsHumanity's Last Exam+27.7points ahead
- Answers hard knowledge questions correctlyAA-Omniscience · Accuracy+26.7points ahead
- Hard command-line tasks in a real terminalTerminal-Bench Hard+25points ahead
Where GPT-5 Codex pulls ahead
- Follows unfamiliar, precisely checkable instructionsIFBench+10.6points ahead
Every test, side by side
All 17 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingClaude Fable 5
- Terminal-Bench HardClaude Fable 5 by 2562.937.9+25
- SWE-bench VerifiedClaude Fable 5 by 20.59574.5+20.5
- SciCodeClaude Fable 5 by 20.16140.9+20.1
ReasoningClaude Fable 5
- Humanity's Last ExamClaude Fable 5 by 27.755.527.8+27.7
- CritPtClaude Fable 5 by 23.528.65.1+23.5
- GPQA DiamondClaude Fable 5 by 8.992.683.7+8.9
FactsClaude Fable 5
- AA-Omniscience · AccuracyClaude Fable 5 by 26.765.338.7+26.7
- AA-Omniscience · Non-hallucinationClaude Fable 5 by 11.836.424.6+11.8
Images and chartsClaude Fable 5
- MMMU-ProClaude Fable 5 by 10.484.273.8+10.4
Following instructionsGPT-5 Codex
- IFBenchGPT-5 Codex by 10.663.574.1+10.6
Other results5 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 Fable 5 by 50.843.3-7.5+50.8
- Artificial Analysis Coding IndexClaude Fable 5 by 37.676.538.9+37.6
- AA IntelligenceClaude Fable 5 by 24.749.624.9+24.7
- τ²-Bench Telecom (AA run)Claude Fable 5 by 11.798.586.8+11.7
- AA Agentic IndexGPT-5 Codex by 1.75152.7+1.7
Questions people ask
Which is better, Claude Fable 5 or GPT-5 Codex?
Claude Fable 5 wins six of the seven areas where both have results: coding, agents, reasoning, facts, images and charts and long documents. GPT-5 Codex wins following instructions, and costs 81% less.
Which is better for coding?
Claude Fable 5. It wins 3 of the 3 coding tests both models report; GPT-5 Codex wins none.
Which is cheaper?
Claude Fable 5 costs $10.00 per million input tokens and $50.00 per million output tokens; GPT-5 Codex costs $1.25 and $10.00. That makes GPT-5 Codex about 81% cheaper for the same work.
How do you compare the two?
We use the 17 benchmark tests both models have published scores on. The verdict counts the 12 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 5 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.