BenchLeader
Sapiens AIReasoning modelAuto-detected

Agnes 2.5 Pro Beta

Not yet ranked: too few independent results so far.

Blended price
$0.150/M
$0.100 in · $0.300 out
Output speed
First answer
Context
1M
How it scores by categoryDashed line = average model (50). One step of 15 = one standard deviation.
  1. Knowledge59
  2. Multimodal60
  3. Long context68
  4. Composite73

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 index90.5%#59Artificial Analysis
Humanity's Last Exam (AA)not in index37.5%#68Artificial Analysis

Coding

BenchmarkdefaultSource
SciCode (AA)not in index48.8%#77Artificial Analysis

Knowledge

BenchmarkdefaultSource
AA-Omniscience-10.5#143Artificial Analysis

Multimodal

BenchmarkdefaultSource
MMMU-Pro75.4%#71Artificial Analysis

Long context

BenchmarkdefaultSource
AA-LCR83.0%#12Artificial Analysis

Composite

BenchmarkdefaultSource
AA Intelligence Index35.2#52Artificial 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$0.0001
Summarise a 30-page report12,000 / 600$0.0014
Code edit6,000 / 1,500$0.0011
Agentic coding session60,000 / 4,000$0.0072
Structured extraction2,000 / 200$0.0003

See also

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