union-alpha wins more areas, narrowly.Claude Opus 4.5 is better at following instructions.
Scores updated · 7 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.
Reasoning, 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 union-alpha pulls ahead
- Fixes real GitHub issues, working as an agentLiveBench · Agentic Coding+15points ahead
- Fresh competition math problemsLiveBench · Mathematics+4.9points ahead
- Programming problems, refreshed regularlyLiveBench · Coding+2.5points ahead
Where Claude Opus 4.5 pulls ahead
- Follows detailed instructions exactlyLiveBench · Instruction Following+3.1points ahead
Every test, side by side
All 7 tests both models report. The winning score is in its model's colour; marks a score checked independently.
Codingunion-alpha
- LiveBench · Agentic Codingunion-alpha by 1539.754.7+15
- LiveBench · Codingunion-alpha by 2.579.782.2+2.5
Following instructionsClaude Opus 4.5
- LiveBench · Instruction FollowingClaude Opus 4.5 by 3.162.559.5+3.1
Other results2 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.
- livebench_languageunion-alpha by 4.681.385.9+4.6
- livebench_data_analysistie74.474.6tie
Questions people ask
Which is better, Claude Opus 4.5 or union-alpha?
union-alpha wins two of the four areas where both have results: coding and math. Claude Opus 4.5 wins following instructions. They are level on reasoning.
Which is better for coding?
union-alpha. It wins 2 of the 2 coding tests both models report; Claude Opus 4.5 wins none.
How do you compare the two?
We use the 7 benchmark tests both models have published scores on. The verdict counts the 5 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 2 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.