Sapiens AIAgnes 2.5 Pro Beta
Agnes 2.5 Pro Beta is a Sapiens AI proprietary reasoning model, released 26 Aug 2026. Its best configuration ranks #138 of 785 on the BenchLeader Index at 59.1 ±3.6, in the upper half. The ± is the point: 221 other configurations score within that range, so they and this one cannot be told apart on quality alone — price and speed are what separate them. It scores highest in composite (69) and lowest in knowledge (57). At $0.150 per million tokens blended it is among the cheapest fifth of ranked models. Output speed of 113 tokens per second puts it faster than most, with a first answer in 19.1 s. Last measured 26 Aug 2026.
- Blended price
- $0.150/M
- $0.100 in · $0.300 out
- Output speed
- 113 tok/s
- measured by Artificial Analysis
- First answer
- 19 s
- Context
- 1M
- Full answer
- 24 s
- median, reasoning included
- Cost per run
- –
- Released
- 26 Aug 2026
- Overall index59
- Reasoning67
- Agents & tools65
- Knowledge57
- Multimodal58
- Long context67
- Composite69
How its index has moved
19 Sept 2026 to 20 Oct 2026The index is recomputed from scratch every day, so a line moves when a new benchmark result lands, when a publisher revises a score, or when the models it is normalised against change. Early movement usually means the score is still settling.
Benchmark results
See all LLM benchmarks. 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
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| GPQA Diamond (AA)not in index | 90.5%#59 | Artificial Analysis | |
| Humanity's Last Exam (AA)not in index | 37.5%#103 | Artificial Analysis | |
| CritPt | 15.7%#88 | Artificial Analysis |
Coding
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| SciCode (AA)not in index | 48.8%#122 | Artificial Analysis | |
| Terminal-Bench 2.1 (AA)not in index | 69.7%#73 | Artificial Analysis |
Agents & tools
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| GDPval-AA v2.1not in index | 41.5%#59 | Artificial Analysis | |
| τ³-Banking (AA) | 35.7%#45 | Artificial Analysis |
Knowledge
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| AA-Omniscience | -10.5#196 | Artificial Analysis | |
| AA-Omniscience: accuracynot in index | 16.8%#380 | Artificial Analysis | |
| AA-Omniscience: non-hallucinationnot in index | 67.2%#55 | Artificial Analysis |
Multimodal
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| MMMU-Pro | 75.4%#99 | Artificial Analysis |
Long context
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| AA-LCR | 83.0%#26 | Artificial Analysis |
Composite
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| AA Intelligence Index v4.3.2 | 35.2#88 | Artificial 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.
| Workload | Tokens in / out | Cost | With caching | Time |
|---|---|---|---|---|
| Chat reply | 400 / 300 | $0.0001 | – | 21.7 s |
| Summarize a 30-page report | 12,000 / 600 | $0.0014 | – | 24.4 s |
| Code edit | 6,000 / 1,500 | $0.0011 | – | 32.4 s |
| Agentic coding session | 60,000 / 4,000 | $0.0072 | – | 54.5 s |
| Structured extraction | 2,000 / 200 | $0.0003 | – | 20.9 s |
See also
Questions people ask
- What are Agnes 2.5 Pro Beta's benchmark scores?
- As of 25 Oct 2026, Agnes 2.5 Pro Beta scores 59.1 ±3.6 on the BenchLeader Index, strongest in composite (69) and weakest in knowledge (57). That rests on 6 independent benchmark results, and every score on this page links to its publisher.
- How does Agnes 2.5 Pro Beta rank?
- Agnes 2.5 Pro Beta is #138 of 785 ranked configurations on 25 Oct 2026. 221 other configurations score within its margin, so the exact position matters less than the band. The leader is Claude Opus 5.5 (max effort) at 72.6.
- How much does Agnes 2.5 Pro Beta cost per 1M tokens?
- As of 25 Oct 2026, Agnes 2.5 Pro Beta costs $0.100 per 1M input tokens and $0.300 per 1M output tokens, $0.150 blended (three input tokens per output token).
- When was Agnes 2.5 Pro Beta released?
- Sapiens AI released Agnes 2.5 Pro Beta on 26 Aug 2026.
Data as of 25 Oct 2026. Compare with another model.
Cite as: BenchLeader, “Agnes 2.5 Pro Beta: benchmarks, pricing, speed and rank”, data as of 25 Oct 2026, https://www.benchleader.com/models/agnes-2-5-pro.