BenchLeader
Sapiens AIOpen weightsReasoning modelAuto-detected

Agnes 2.5 Pro Alpha

Not yet ranked: too few independent results so far. Released 24 Jul 2026.

Blended price
$0.563/M
$0.450 in · $0.900 out
Output speed
174 tok/s
First answer
14 s
Context
1M
How it scores by categoryDashed line = average model (50). One step of 15 = one standard deviation.
  1. Knowledge52
  2. Long context64
  3. Composite63

Benchmark results

One column per reasoning effort. Rank is among every configuration of every model on that benchmark. Hover a score for the run it came from.

Reasoning

BenchmarkdefaultSource
GPQA Diamond (AA)not in index87.6%#95Artificial Analysis
Humanity's Last Exam (AA)not in index33.6%#89Artificial Analysis

Coding

BenchmarkdefaultSource
SciCode (AA)not in index42.9%#101Artificial Analysis

Knowledge

BenchmarkdefaultSource
AA-Omniscience-25.1#199Artificial Analysis

Long context

BenchmarkdefaultSource
AA-LCR75.7%#107Artificial Analysis

Composite

BenchmarkdefaultSource
AA Intelligence Index26.8#103Artificial Analysis

What a task costs

Estimates from list price, output speed and time to first answer for the best configuration. “With caching” assumes three-quarters of the input is served from the prompt cache. Reasoning tokens are not modelled.

WorkloadTokens in / outCostWith cachingTime
Chat reply400 / 300$0.000516.1 s
Summarise a 30-page report12,000 / 600$0.005917.9 s
Code edit6,000 / 1,500$0.004123.1 s
Agentic coding session60,000 / 4,000$0.03137.5 s
Structured extraction2,000 / 200$0.001115.6 s

See also

Data as of 9 Sept 2026. Compare with another model.