# Gemini 2.5 ProHigh

> Source: Benchize (https://benchize.com) — https://benchize.com/models/gemini-2-5-pro-high. When citing or reusing this content, credit "Benchize" and link to https://benchize.com/models/gemini-2-5-pro-high.

Google

Canonical URL: https://benchize.com/models/gemini-2-5-pro-high
Last updated: Thu, 22 Oct 2026 08:00:11 GMT

Reproduction and quotation must name Benchize, link to the canonical HTML URL, and retain individual source citations.

Google

## Benchmarks

| Benchmark | Score | Rank |  |
| --- | --- | --- | --- |
| [τ-bench banking knowledge](https://benchize.com/benchmarks/sierra%3Abanking_knowledge.md) | 13.66% | 17 / 19 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `pass_1` \| 13.66 \| percent \| consistent_success_across_k_trials \| Higher is better \| \| `pass_2` \| 6.01 \| percent \| consistent_success_across_k_trials \| Higher is better \| \| `pass_3` \| 2.58 \| percent \| consistent_success_across_k_trials \| Higher is better \| \| `pass_4` \| 1.03 \| percent \| consistent_success_across_k_trials \| Higher is better \| ### Configuration benchmarkVersion 1.0.1 harness tau-bench methodology {"evaluation_date":"2026-05-05","notes":"Evaluated using AllTools retrieval (BM25 + dense OpenAI text-embedding-3-large + sandboxed shell). User simulator: gpt-5.2 with reasoning_effort: low. 4 trials. Seed: 300. Banking_knowledge domain only — other domains intentionally excluded from this comparison; the AllTools setting standardizes retrieval across models. banking_knowledge re-graded under tau2-bench v1.0.1 grading fixes on 2026-07-15 (extra-read logging #329, numeric-argument normalization #397, T077-T086 gold trajectories #402); scores prior to v1.0.1 are not comparable.","tau2_bench_version":"1.0.1","user_simulator":"gpt-5.2","verification":{"details":"Banking_knowledge domain only, AllTools retrieval. Trajectories suppressed for this preliminary AllTools comparison; raw per-task results retained internally.","modified_prompts":false,"omitted_questions":false}} modality text Reasoning effort high retrieval alltools sourceSubmission gemini-2-5-pro_sierra_2026-05-05 ### Source [Original source](https://sierra-tau-bench-public.s3.us-west-2.amazonaws.com/submissions/gemini-2-5-pro_sierra_2026-05-05/submission.json) Source sierra Original model label Gemini 2.5 Pro Evaluated 2026-05-05 Observed 2026-10-21T16:54:50.453Z Evidence SHA-256 `b14f65b54ac7b733550cb1e04b986d17b7ff877de6ff79e94e8e98998035de6f` Source locator `/results/banking_knowledge` |  |  |  |

---
Cite as: Gemini 2.5 ProHigh — Benchize, https://benchize.com/models/gemini-2-5-pro-high (retrieved 2026-10-22)