Agnes 2.5 Pro Beta vs G9v3-3B
Wins 4 of 5 areas
Coding · Agents · Reasoning · Long documents
Wins 0 of 5 areas
—
Agnes 2.5 Pro Beta is the stronger all-rounder.
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 thinking30Agnes 2.5 Pro Beta3 of 3 tests
- CodingWriting and fixing software20Agnes 2.5 Pro Beta2 of 2 tests
- AgentsCarrying out multi-step tasks on its own20Agnes 2.5 Pro Beta2 of 2 tests
- Long documentsFinding answers in very long texts10Agnes 2.5 Pro Beta1 of 1 test
- FactsGetting facts right instead of making them up11Even1 each
Long documents rests on a single test.
The biggest differences
The tests each model wins by the widest margin, up to three each. Scores are out of 100.
Where Agnes 2.5 Pro Beta pulls ahead
- Command-line tasks in a real terminalTerminal-Bench 2.1+63.7points ahead
- Graduate-level biology, physics and chemistry questionsGPQA Diamond+46.7points ahead
- Reasons across sets of long documentsAA-LCR+41.7points ahead
Where G9v3-3B pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+21.1points 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.
CodingAgnes 2.5 Pro Beta
- Terminal-Bench 2.1Agnes 2.5 Pro Beta by 63.769.76+63.7
- SciCodeAgnes 2.5 Pro Beta by 31.148.817.7+31.1
AgentsAgnes 2.5 Pro Beta
- τ-Bench V3 · BankingAgnes 2.5 Pro Beta by 29.935.75.8+29.9
- GDPValAgnes 2.5 Pro Beta by 25.240.615.4+25.2
ReasoningAgnes 2.5 Pro Beta
- GPQA DiamondAgnes 2.5 Pro Beta by 46.790.543.8+46.7
- Humanity's Last ExamAgnes 2.5 Pro Beta by 3337.54.5+33
- CritPtAgnes 2.5 Pro Beta by 15.715.70+15.7
FactsEven
- AA-Omniscience · Non-hallucinationG9v3-3B by 21.167.288.3+21.1
- AA-Omniscience · AccuracyAgnes 2.5 Pro Beta by 10.316.86.5+10.3
Long documentsAgnes 2.5 Pro Beta
- AA-LCRAgnes 2.5 Pro Beta by 41.78341.3+41.7
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.
- Artificial Analysis Coding IndexAgnes 2.5 Pro Beta by 52.462.39.9+52.4
- AA Agentic IndexAgnes 2.5 Pro Beta by 29.843.814+29.8
- AA IntelligenceAgnes 2.5 Pro Beta by 24.435.210.8+24.4
- AA-OmniscienceG9v3-3B by 6.1-10.5-4.4+6.1
Questions people ask
Which is better, Agnes 2.5 Pro Beta or G9v3-3B?
Agnes 2.5 Pro Beta wins four of the five areas where both have results: coding, agents, reasoning and long documents. G9v3-3B wins none. They are level on facts.
Which is better for coding?
Agnes 2.5 Pro Beta. It wins 2 of the 2 coding tests both models report; G9v3-3B wins none.
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.