Beam 1.0 vs Claude Opus 4.8
Wins 1 of 5 areas
Following instructions
Wins 4 of 5 areas
Coding · Agents · Reasoning · Math
Claude Opus 4.8 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 five 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 software05Claude Opus 4.85 of 5 tests
- ReasoningHard problems that need careful thinking04Claude Opus 4.84 of 4 tests
- AgentsCarrying out multi-step tasks on its own02Claude Opus 4.82 of 2 tests
- MathCompetition and research-level math01Claude Opus 4.81 of 1 test
- Following instructionsDoing exactly what it is asked10Beam 1.01 of 1 test
Math 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.
The biggest differences
The tests each model wins by the widest margin, up to three each. Scores are out of 100.
Where Claude Opus 4.8 pulls ahead
- Abstract visual puzzles that people can solveARC-AGI-2+48.6points ahead
- Very hard expert questions across many subjectsHumanity's Last Exam+12.7points ahead
- Finds hard-to-locate facts by browsing the webBrowseComp+7.5points ahead
Where Beam 1.0 pulls ahead
- Follows unfamiliar, precisely checkable instructionsIFBench+17.4points 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 Opus 4.8
- SWE-bench VerifiedClaude Opus 4.8 by 781.688.6+7
- SWE-bench MultilingualClaude Opus 4.8 by 6.178.384.4+6.1
- SciCodeClaude Opus 4.8 by 5.249.254.4+5.2
- Terminal-Bench 2.1Claude Opus 4.8 by 4.580.184.6+4.5
- SWE-bench ProClaude Opus 4.8 by 3.166.169.2+3.1
AgentsClaude Opus 4.8
- BrowseCompClaude Opus 4.8 by 7.576.884.3+7.5
- MCP AtlasClaude Opus 4.8 by 1.480.882.2+1.4
ReasoningClaude Opus 4.8
- ARC-AGI-2Claude Opus 4.8 by 48.623.572.1+48.6
- Humanity's Last ExamClaude Opus 4.8 by 12.73648.7+12.7
- CritPtClaude Opus 4.8 by 4.616.320.9+4.6
- GPQA DiamondClaude Opus 4.8 by 1.490.692+1.4
Following instructionsBeam 1.0
- IFBenchBeam 1.0 by 17.479.662.2+17.4
Other results4 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.
- ARC-AGI-1Claude Opus 4.8 by 18.57492.5+18.5
- DeepSWE 1.1Claude Opus 4.8 by 15.743.359+15.7
- DeepSearchQA (F1)Claude Opus 4.8 by 12.680.593.1+12.6
- HLE (with tools)Claude Opus 4.8 by 6.851.157.9+6.8
Questions people ask
Which is better, Beam 1.0 or Claude Opus 4.8?
Claude Opus 4.8 wins four of the five areas where both have results: coding, agents, reasoning and math. Beam 1.0 wins following instructions.
Which is better for coding?
Claude Opus 4.8. 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 13 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 4 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.