Agnes 2.5 Pro Alpha vs G9v3-39A5B
Wins 3 of 5 areas
Coding · Reasoning · Long documents
Wins 1 of 5 areas
Agents
Agnes 2.5 Pro Alpha is the stronger all-rounder.G9v3-39A5B is better at agents.
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 Alpha3 of 3 tests
- CodingWriting and fixing software20Agnes 2.5 Pro Alpha2 of 2 tests
- Long documentsFinding answers in very long texts10Agnes 2.5 Pro Alpha1 of 1 test
- AgentsCarrying out multi-step tasks on its own02G9v3-39A5B2 of 2 tests
- FactsGetting facts right instead of making them up11Even1 each
Long documents rests on a single test.
The biggest differences
The three tests each model wins by the widest margin. Scores are out of 100.
Where Agnes 2.5 Pro Alpha pulls ahead
- Command-line tasks in a real terminalTerminal-Bench 2.1+34.4points ahead
- Answers hard knowledge questions correctlyAA-Omniscience · Accuracy+18.6points ahead
- Very hard expert questions across many subjectsHumanity's Last Exam+16.1points ahead
Where G9v3-39A5B pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+75.1points ahead
- Customer-service tasks in a simulated bankτ-Bench V3 · Banking+9.7points ahead
- Real work tasks from 44 professionsGDPVal+1.1points 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 Alpha
- Terminal-Bench 2.1Agnes 2.5 Pro Alpha by 34.46732.6+34.4
- SciCodeAgnes 2.5 Pro Alpha by 6.142.936.8+6.1
AgentsG9v3-39A5B
- τ-Bench V3 · BankingG9v3-39A5B by 9.712.422.1+9.7
- GDPValG9v3-39A5B by 1.129.430.5+1.1
ReasoningAgnes 2.5 Pro Alpha
- Humanity's Last ExamAgnes 2.5 Pro Alpha by 16.133.617.5+16.1
- CritPtAgnes 2.5 Pro Alpha by 10.610.90.3+10.6
- GPQA DiamondAgnes 2.5 Pro Alpha by 7.187.680.5+7.1
FactsEven
- AA-Omniscience · Non-hallucinationG9v3-39A5B by 75.111.987+75.1
- AA-Omniscience · AccuracyAgnes 2.5 Pro Alpha by 18.633.514.9+18.6
Long documentsAgnes 2.5 Pro Alpha
- AA-LCRAgnes 2.5 Pro Alpha by 10.475.765.3+10.4
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.
- AA-OmniscienceG9v3-39A5B by 28.9-25.13.8+28.9
- Artificial Analysis Coding IndexAgnes 2.5 Pro Alpha by 25.758.833.1+25.7
- AA IntelligenceAgnes 2.5 Pro Alpha by 526.821.8+5
- AA Agentic IndexG9v3-39A5B by 3.529.432.9+3.5
Questions people ask
Which is better, Agnes 2.5 Pro Alpha or G9v3-39A5B?
Agnes 2.5 Pro Alpha wins three of the five areas where both have results: coding, reasoning and long documents. G9v3-39A5B wins agents. They are level on facts.
Which is better for coding?
Agnes 2.5 Pro Alpha. It wins 2 of the 2 coding tests both models report; G9v3-39A5B 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.