Agnes 2.5 Pro Beta
Agnes 2.5 Pro Beta is strong in long context; capable in reasoning; and behind the leaders in multimodal tasks, agentic tasks, factuality, and coding. Too few results yet to rate safety, math, multilingual tasks, or instruction following.
Capability profile
Bars show the model's median result as a share of the leading model's, per capability. Select a row to see its results.
Too few results yet to rate Safety, Math, Multilingual or Instruction Following.
Price
No current price is tracked for this model. See the rate card
Evidence
15results on15benchmarks
- 15 aggregator
From 1 source · latest Oct 16, 2026 · How verification works
Agnes 2.5 Pro Beta benchmark results
15 results on 15 benchmarks, grouped by capability. Each bar is the result as a share of the capability leader's; every result links to its source.
6.7% behind the leader1 of 3 ranked benchmarks measured
- 83.00Oct 16, 2026
20.1% behind the leader3 of 6 ranked benchmarks measured
- GPQA Diamond90.51Oct 16, 2026gpqa
- Humanity's Last Exam37.53Oct 16, 2026aa_hle
- 15.71Oct 16, 2026
28.2% behind the leader1 of 6 ranked benchmarks measured
- MMMU-Pro75.43Oct 16, 2026aa_mmmu_pro
29.1% behind the leader2 of 7 ranked benchmarks measured
- τ-Bench V3 · Banking35.67Oct 16, 2026tauBanking
- 41.43Oct 16, 2026
31.4% behind the leader2 of 4 ranked benchmarks measured
- AA-Omniscience · Non-hallucination67.20Oct 16, 2026omniscienceNonHallucination
- AA-Omniscience · Accuracy16.77Oct 16, 2026omniscienceAccuracy
32.9% behind the leader2 of 10 ranked benchmarks measured
- Terminal-Bench 2.169.66Oct 16, 2026terminalbenchV21
- SciCode48.84Oct 16, 2026aa_scicode
More results
Benchmarks outside the capability baskets. They are not ranked against a leader.
- AA Intelligence35.24Oct 16, 2026aa_intelligence_index
- -10.53Oct 16, 2026
- Artificial Analysis Coding Index62.30Sep 9, 2026aa_coding_index
- 43.77Sep 4, 2026
Agnes 2.5 Pro Beta: common questions
Who makes Agnes 2.5 Pro Beta?
Agnes 2.5 Pro Beta is made by Sapiens AI.
When was Agnes 2.5 Pro Beta released?
Agnes 2.5 Pro Beta was released on Aug 26, 2026, according to Artificial Analysis.
What is Agnes 2.5 Pro Beta good at?
Agnes 2.5 Pro Beta is strong in long context; capable in reasoning; and behind the leaders in multimodal tasks, agentic tasks, factuality, and coding. Too few results yet to rate safety, math, multilingual tasks, or instruction following.
How many benchmarks has Agnes 2.5 Pro Beta been tested on?
We track 15 results for Agnes 2.5 Pro Beta on 15 benchmarks from 1 source. The latest was recorded on Oct 16, 2026.
About this record
Where Agnes 2.5 Pro Beta's numbers come from, and every name it appears under.
- Tracked since
- Aug 27, 2026
- Newest source mention
- Aug 27, 2026
Where the results come from
Verification: 15 scores · 0 independently verified · 15 aggregator-attributed. How these tiers are assigned
From 1 source on 1 site. Artificial Analysis supplies all of them. Bars are coloured by trust tier.
- artificialanalysis.ai15