Agnes 2.5 Pro Beta vs Claude Opus 4.8
Wins 1 of 5 areas
Long documents
Wins 2 of 5 areas
Coding · Reasoning
Claude Opus 4.8 wins more areas, narrowly.Agnes 2.5 Pro Beta is cheaper and better at long documents.
Scores updated · 14 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.
- ReasoningHard problems that need careful thinking03Claude Opus 4.83 of 3 tests
- CodingWriting and fixing software02Claude Opus 4.82 of 2 tests
- Long documentsFinding answers in very long texts10Agnes 2.5 Pro Beta1 of 1 test
- AgentsCarrying out multi-step tasks on its own11Even1 each
- FactsGetting facts right instead of making them up11Even1 each
Long documents 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.
Agnes 2.5 Pro Beta costs 99% less for the same work.
The biggest differences
The three tests each model wins by the widest margin. Scores are out of 100.
Where Claude Opus 4.8 pulls ahead
- Answers hard knowledge questions correctlyAA-Omniscience · Accuracy+32points ahead
- Command-line tasks in a real terminalTerminal-Bench 2.1+14.9points ahead
- Very hard expert questions across many subjectsHumanity's Last Exam+11.2points ahead
Where Agnes 2.5 Pro Beta pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+6.5points ahead
- Reasons across sets of long documentsAA-LCR+5.3points ahead
- Customer-service tasks in a simulated bankτ-Bench V3 · Banking+1.5points ahead
Every test, side by side
All 14 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingClaude Opus 4.8
- Terminal-Bench 2.1Claude Opus 4.8 by 14.969.784.6+14.9
- SciCodeClaude Opus 4.8 by 5.648.854.4+5.6
AgentsEven
- GDPValClaude Opus 4.8 by 6.341.447.7+6.3
- τ-Bench V3 · BankingAgnes 2.5 Pro Beta by 1.535.734.2+1.5
ReasoningClaude Opus 4.8
- Humanity's Last ExamClaude Opus 4.8 by 11.237.548.7+11.2
- CritPtClaude Opus 4.8 by 5.215.720.9+5.2
- GPQA DiamondClaude Opus 4.8 by 1.590.592+1.5
FactsEven
- AA-Omniscience · AccuracyClaude Opus 4.8 by 3216.848.8+32
- AA-Omniscience · Non-hallucinationAgnes 2.5 Pro Beta by 6.567.260.7+6.5
Long documentsAgnes 2.5 Pro Beta
- AA-LCRAgnes 2.5 Pro Beta by 5.38377.7+5.3
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.
- AA-OmniscienceClaude Opus 4.8 by 39.3-10.528.8+39.3
- Artificial Analysis Coding IndexClaude Opus 4.8 by 1262.374.3+12
- AA IntelligenceClaude Opus 4.8 by 6.635.241.8+6.6
- AA Agentic IndexAgnes 2.5 Pro Beta by 1.243.842.6+1.2
Questions people ask
Which is better, Agnes 2.5 Pro Beta or Claude Opus 4.8?
Claude Opus 4.8 wins two of the five areas where both have results: coding and reasoning. Agnes 2.5 Pro Beta wins long documents, and costs 99% less. They are level on agents and facts.
Which is better for coding?
Claude Opus 4.8. It wins 2 of the 2 coding tests both models report; Agnes 2.5 Pro Beta wins none.
Which is cheaper?
Agnes 2.5 Pro Beta costs $0.10 per million input tokens and $0.30 per million output tokens; Claude Opus 4.8 costs $5.00 and $25.00. That makes Agnes 2.5 Pro Beta about 99% cheaper for the same work.
How do you compare the two?
We use the 14 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 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.