Benchmark Almanac

τc-Bench

Gemini 3 Flash 87.7% leads since May 2026
Not in model cards
Version Contextual

Agents use tools while conversing with simulated customers in airline, retail, and telecom tasks. The evaluator compares the final environment state with the expected state. Generated scenarios add unusual tool combinations, ambiguous requests, and distracting database records.

This extension changes the tasks from τ²-Bench rather than only fixing them. The TASTE synthesis method is unrelated to Anthropic’s TASTE benchmark.

Made by
Technion and IBM Research
Released
May 2026
Kind
Customer service
Level
Everyday
Scored
Checked automatically
Answers
Agent task
Tasks
All public
Measures
Capability
Language
English
In and out
Text → Actions, Text
Interaction
Agentic
Environment
APIs and tools
Run by
Anyone
Based on
tau2-bench
In views
Agents
Strongest model tested
GPT-5.2 #51 on the capability index
Last model added
December 2025
Scores refreshed
November 20th, 2026

In the authors’ words

As agent capabilities advance, existing benchmarks, such as τ²-Bench, are becoming increasingly saturated. Yet constructing new benchmark tasks remains complex, costly, and labor-intensive. Moreover, the standard approach, in which scenarios are first written in natural language and then mapped to tool sequences, captures only a narrow subset of the tool-use patterns agents exercise. In this paper, we address these problems by reversing the task construction process. We propose TASTE: Task Synthesis from Tool Sequence Evolution, an automatic method that generates challenging tasks with broader tool-use coverage. TASTE utilizes an Adaptive Contrastive n-gram model trained on LLM-judged validity signals. This enables sampling valid tool sequences that cover a vast range of tool combinations. TASTE then selects representative sequences from the pool via clustering, instantiates them into complete benchmark tasks, and refines them through iterative difficulty evolution. Using TASTE, we construct τc-Bench, a challenging extension of the three domains of τ²-Bench. We evaluate 11 agent/user LLM pairs and find that models nearly saturating τ²-Bench suffer severe performance drops on our tasks (e.g., Gemini-3-Flash falls from 0.82 - 0.94 to 0.28 - 0.61). Beyond increasing difficulty, our generated tasks more than double the number of unique tool combinations agents must execute. Our results suggest high scores on existing benchmarks often reflect saturation rather than robust task-solving ability. By automating the generation of difficult, high-coverage benchmarks, TASTE enables continuous, scalable evaluation of future agents.

Abstract of A Matter of TASTE: Improving Coverage and Difficulty of Agent Benchmarks (arXiv:2605.28556, CC0)
5
Entries in its paper, 3 models we track

Gemini 3 Flash leads with 87.7% among models released by December 2025 Gemini 3 Flash leads with 87.7% among models released by December 2025

Best score per entry from the benchmark's paper, read on November 20th, 2026. A paper’s table doesn’t add newer models. The paper reports no overall score, so this is the plain mean of Airline, Retail and Telecom pass^1 scores. Where a model ran with several settings or harnesses, we keep its best. Every run is in the next chart. Names in gray aren't in our model list: fine-tunes, agent systems, products and older models. They don't count toward leaders. This view shows only models we track, each at its best.

The newest model with a score here came out in December 2025, and nobody has tested a newer one. Among the 20 highest-ranked models on the capability index, these have no score yet:

  1. 1 Gemini 3 Flash user simulator: GPT-5.2 87.7%
  2. 2 GPT-5.2 user simulator: Gemini-3-flash 68%
  3. 3 deepseek-3.1 user simulator: GPT-5.2 65%
  4. 4 Gemini 2.5 Flash Sep 2025, user simulator: Gemini-3-flash 57.3%
  5. 5 Qwen-32B user simulator: Gemini-3-flash 46%

Source: The τc-Bench paper

#EntryScoreSettingDateSource
1 Gemini 3 Flash 87.7% user simulator: GPT-5.2 Dec 2025 Official leaderboard
2 GPT-5.2 68% user simulator: Gemini-3-flash Dec 2025 Official leaderboard
3 deepseek-3.1 65% user simulator: GPT-5.2 Official leaderboard
4 Gemini 2.5 Flash Sep 2025 57.3% user simulator: Gemini-3-flash Sep 2025 Official leaderboard
5 Qwen-32B 46% user simulator: Gemini-3-flash Official leaderboard
#ModelScoreSettingDateSource
1 Gemini 3 Flash 87.7% user simulator: GPT-5.2 Dec 2025 Official leaderboard
2 GPT-5.2 68% user simulator: Gemini-3-flash Dec 2025 Official leaderboard
3 Gemini 2.5 Flash Sep 2025 57.3% user simulator: Gemini-3-flash Sep 2025 Official leaderboard

Rankings by part

We read 3 parts from the benchmark’s paper: Airline pass^1, Retail pass^1 and Telecom pass^1. Each ranks models on one part of the test. Gemini 3 Flash leads 2 of them, and GPT-5.2 leads the other one. Arrows show how far a model moved from its overall rank among the models we track.

Airline pass^1

3 models we track have a score here.

  1. 1 Gemini 3 Flash 82%
  2. 2 Gemini 2.5 Flash Sep 2025 ↑1 66%
  3. 3 GPT-5.2 ↓1 58%

Scores at each effort level

Models the leaderboard ran at two or more effort levels. We don’t have enough cost data here to say what the extra effort costs.

Lowest effort to highest, light to dark
Gemini 3 Flash
user simula… user simula…
87.7%
GPT-5.2
user simula… user simula…
68%
Gemini 2.5 Flash
user simula…
57.3%

Source: The τc-Bench paper

ModelEffortHarnessScoreCost per taskOutput tokens
Gemini 3 Flash user simulator: GPT-5.2 87.7%
Gemini 3 Flash user simulator: Gemini-3-flash 83.3%
GPT-5.2 user simulator: Gemini-3-flash 68%
GPT-5.2 user simulator: GPT-5.2 63%
Gemini 2.5 Flash Sep 2025 user simulator: Gemini-3-flash 57.3%
Gemini 2.5 Flash Sep 2025 user simulator: GPT-5.2 57.3%

Scores at each effort level

Models the leaderboard ran at two or more effort levels. We don’t have enough cost data here to say what the extra effort costs.

Lowest effort to highest, light to dark
Gemini 3 Flash
user simula… user simula…
87.7%
GPT-5.2
user simula… user simula…
68%
Gemini 2.5 Flash
user simula…
57.3%

Source: The τc-Bench paper

ModelEffortHarnessScoreCost per taskOutput tokens
Gemini 3 Flash user simulator: GPT-5.2 87.7%
Gemini 3 Flash user simulator: Gemini-3-flash 83.3%
GPT-5.2 user simulator: Gemini-3-flash 68%
GPT-5.2 user simulator: GPT-5.2 63%
Gemini 2.5 Flash Sep 2025 user simulator: Gemini-3-flash 57.3%
Gemini 2.5 Flash Sep 2025 user simulator: GPT-5.2 57.3%

Number one over time

Lab claims count from the day the card came out, independent runs from the model’s release.

Google DeepMind
Benchmark paper Passed 85% in May 2026, by Gemini 3 Flash

Source: The τc-Bench paper

Gemini 3 Flash on the official leaderboard passed 85% in December 2025

Models released before it came out already scored that high. All the scores we have, one dot each, so a model tested at several settings appears more than once.

Plot with other benchmarks
In the benchmark’s paper Best so far
0% 20% 40% 60% 80% 100% 2026 Near the ceiling (85%) Gemini 3 Flash GPT-5.2 Gemini 2.5 Flash 0% 20% 40% 60% 80% 100% 2026 Near the ceiling (85%) Gemini 3 Flash GPT-5.2

Source: Official τc-Bench leaderboard

No lab model card reports it yet

We read the headline results of 540 launch posts from 57 labs, and none of them list this benchmark.

Versions

We switch the top row to each new version when it comes out. Open it for one row per version. An old version stays in play while people still test it, so whoever first takes it past 85% gets credit for closing it out.

Anthropic OpenAI Moonshot AI MiniMax Qwen Xiaomi Corp NVIDIA Inception Labs Google DeepMind
τ-bench 2.0 Not tested since Oct 2026
GPT-Live-1 79.9%
tau-bench Replaced by tau2-bench, Sep 2025
tau2-bench Passed 85% in Oct 2025, by MiniMax-M2
GPT-5.4 98.9%
tau3-bench Passed 85% in Jun 2026, by Nemotron 3 Ultra
τc-Bench Passed 85% in May 2026, by Gemini 3 Flash
τ-bench 2.0 Not tested since Oct 2026
GPT-Live-1 79.9%

Sources: Official leaderboards and labs’ model cards

More in Tool use

All 265 in Tool use
  • AutomationBench In use Agent completes end-to-end business workflows inside a simulated company exposing dozens of REST APIs. Graded on resulting state. Gemini 4 Neon 56.3%
  • MCP Atlas In use Multi-step workflows over real MCP servers. Scores tool-use competency on realistic tasks. Gemini 4 Argon 90.7%
  • BFCL V4 In use Models call functions and tools, including multi-turn agentic tasks with web search and memory. Checked against expected calls and outcomes. Qwen3.7-Max 75%
  • τ³-bench Banking In use Agents act as banking customer-service reps over many turns with a simulated user, following policy. Pass^1 on the final database state. Qwen 3.8 Max 55.1%
  • Toolathlon-Verified In use 108 long-horizon tasks across 32 apps through about 600 MCP tools. Execution-based checkers inspect final environment state. GLM-5.3-Flash 78.4%
  • DeepSearchQA In use Questions that need multi-step search and synthesis. Final answers graded against references. Kimi K3 95%

Data audit

All 8 checks pass. Every benchmark

Catalog record 2 pass
  • Pass Task access All tasks are public.
  • Pass Confidence Checked against a primary source.
Scores 2 pass 3 notes
  • Pass Independent runs Scores from the benchmark’s paper (5 entries).
  • Pass Models scored 3 models we track, plus 2 other entries on its leaderboard.
  • Note Newest score The newest came 11 months ago, in December 2025, for Gemini 3 Flash. That’s expected for a test replaced by τ-bench 2.0.
  • Note Frontier models None of the top 10 has a score, which is fine for a retired test. The strongest tested is GPT-5.2 (#51).
  • Note Headroom Saturated. The best is 87.7%, past 85% since December 2025.
Leaderboard import 3 pass
  • Pass Importer We read the board on arxiv.org: 6 rows for models we track and 2 other entries at the last read.
  • Pass Last read November 20th, 2026.
  • Pass Read worked The last read worked.
Consistency 1 pass 1 note
  • Note Lab claims No model has both a lab number and an independent run.
  • Pass Known issues No published audit found problems.

How we check