Beam 1.0 vs Claude Fable 5
Wins 1 of 4 areas
Following instructions
Wins 3 of 4 areas
Coding · Agents · Reasoning
Claude Fable 5 is the stronger all-rounder.Beam 1.0 is better at following instructions.
Scores updated · 17 tests both models report · How we compare
Where each one wins
Tests won in each of the four 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.
Following instructions rests on a single test.
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.
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
- Abstract visual puzzles that people can solveARC-AGI-2+65.7points ahead
- Very hard expert questions across many subjectsHumanity's Last Exam+19.5points ahead
- Long, multi-file coding tasks in real codebasesSWE-bench Pro+13.9points ahead
Where Beam 1.0 pulls ahead
- Follows unfamiliar, precisely checkable instructionsIFBench+16.1points 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
- SWE-bench ProClaude Fable 5 by 13.966.180+13.9
- SWE-bench VerifiedClaude Fable 5 by 13.481.695+13.4
- SciCodeClaude Fable 5 by 11.849.261+11.8
- SWE-bench MultilingualClaude Fable 5 by 8.378.386.6+8.3
- Terminal-Bench 2.1Claude Fable 5 by 4.580.184.6+4.5
AgentsClaude Fable 5
- BrowseCompClaude Fable 5 by 10.676.887.4+10.6
- MCP AtlasClaude Fable 5 by 3.980.884.7+3.9
ReasoningClaude Fable 5
- ARC-AGI-2Claude Fable 5 by 65.723.589.2+65.7
- Humanity's Last ExamClaude Fable 5 by 19.53655.5+19.5
- CritPtClaude Fable 5 by 12.316.328.6+12.3
- GPQA DiamondClaude Fable 5 by 290.692.6+2
Following instructionsBeam 1.0
- IFBenchBeam 1.0 by 16.179.663.5+16.1
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.
- DeepSWE 1.1Claude Fable 5 by 26.743.370+26.7
- ARC-AGI-1Claude Fable 5 by 24.57498.5+24.5
- DeepSearchQA (F1)Claude Fable 5 by 13.780.594.2+13.7
- HLE (with tools)Claude Fable 5 by 12.751.163.8+12.7
- τ³-Bench BankingBeam 1.0 by 9.336.126.8+9.3
Questions people ask
Which is better, Beam 1.0 or Claude Fable 5?
Claude Fable 5 wins three of the four areas where both have results: coding, agents and reasoning. Beam 1.0 wins following instructions.
Which is better for coding?
Claude Fable 5. It wins 5 of the 5 coding tests both models report; Beam 1.0 wins none.
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.