Agnes 3.0 Flash
Agnes 3.0 Flash is strong in long context; capable in reasoning, agentic tasks, and factuality; and behind the leaders in coding. Too few results yet to rate safety, math, multimodal tasks, 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, Multimodal, Multilingual or Instruction Following.
Price
No current price is tracked for this model. See the rate card
Evidence
13results on13benchmarks
- 13 aggregator
From 1 source · latest Sep 23, 2026 · How verification works
Agnes 3.0 Flash benchmark results
13 results on 13 benchmarks, grouped by capability. Each bar is the result as a share of the capability leader's; every result links to its source.
9.6% behind the leader1 of 3 ranked benchmarks measured
- 81.00Sep 23, 2026
19.2% behind the leader3 of 6 ranked benchmarks measured
- GPQA Diamond92.42Sep 23, 2026gpqa
- Humanity's Last Exam38.46Sep 23, 2026aa_hle
- 15.14Sep 23, 2026
20.4% behind the leader3 of 7 ranked benchmarks measured
- τ-Bench V3 · Banking47.63Sep 23, 2026tauBanking
- 52.50Sep 23, 2026
- Terminal-Bench 4.07.07Sep 23, 2026
25.0% behind the leader2 of 4 ranked benchmarks measured
- AA-Omniscience · Non-hallucination51.62Sep 23, 2026omniscienceNonHallucination
- AA-Omniscience · Accuracy25.48Sep 23, 2026omniscienceAccuracy
31.0% behind the leader2 of 10 ranked benchmarks measured
- Terminal-Bench 2.182.02Sep 23, 2026terminalbenchV21
- SciCode51.62Sep 23, 2026aa_scicode
More results
Benchmarks outside the capability baskets. They are not ranked against a leader.
- AA Intelligence35.50Sep 23, 2026aa_intelligence_index
- -10.57Sep 23, 2026
Agnes 3.0 Flash: common questions
Who makes Agnes 3.0 Flash?
Agnes 3.0 Flash is made by Sapiens AI.
When was Agnes 3.0 Flash released?
Agnes 3.0 Flash was released on Sep 11, 2026, according to Artificial Analysis.
What is Agnes 3.0 Flash good at?
Agnes 3.0 Flash is strong in long context; capable in reasoning, agentic tasks, and factuality; and behind the leaders in coding. Too few results yet to rate safety, math, multimodal tasks, multilingual tasks, or instruction following.
How many benchmarks has Agnes 3.0 Flash been tested on?
We track 13 results for Agnes 3.0 Flash on 13 benchmarks from 1 source. The latest was recorded on Sep 23, 2026.
About this record
Where Agnes 3.0 Flash's numbers come from, and every name it appears under.
- Tracked since
- Sep 12, 2026
- Newest source mention
- Sep 13, 2026
Where the results come from
Verification: 13 scores · 0 independently verified · 13 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.ai13