Benchmark Almanac

Toloka Arena

Claude Opus 4.6 33% leads since April 2026
Not in model cards

Agents handle private simulated enterprise workflows with live databases, API tools and strict business rules across nine domains. The main metric pass^5 needs all five trials to succeed.

Modeled on the tau-bench method. Launch post dated April 16th, 2026.

Made by
Toloka
Released
April 2026
Kind
Customer service
Level
Expert
Scored
Checked automatically
Answers
Agent task
Tasks
Kept private
Strongest model tested
GPT-5.4 #27 on the capability index
Last model added
March 2026
Scores refreshed
November 12th, 2026
5
Models scored on its own leaderboard

Claude Opus 4.6 leads with 33% among models released by March 2026

Best score per model from the benchmark's own leaderboard, read on November 12th, 2026. Where a model ran with several settings or harnesses, we keep its best.

The newest model with a score here came out in March 2026, and nobody has tested a newer one. Among the 20 highest-ranked models on the capability index, these have no score yet:

  1. 33.0 Claude Opus 4.6
  2. 25.2 Gemini 3.1 Pro
  3. 24.9 GPT-5.4
  4. 22.8 Gemini 3 Flash
  5. 21.6 Claude Sonnet 4.6
  1. 1 Claude Opus 4.6 Launch baseline 33%
  2. 2 Gemini 3.1 Pro Launch baseline 25.2%
  3. 3 GPT-5.4 Launch baseline; xhigh reasoning 24.9%
  4. 4 Gemini 3 Flash Launch baseline 22.8%
  5. 5 Claude Sonnet 4.6 Launch baseline 21.6%

Source: Official Toloka Arena leaderboard

#ModelScoreSettingDateSource
1 Claude Opus 4.6 33% Launch baseline Feb 2026 Official leaderboard
2 Gemini 3.1 Pro 25.2% Launch baseline Feb 2026 Official leaderboard
3 GPT-5.4 24.9% Launch baseline; xhigh reasoning Mar 2026 Official leaderboard
4 Gemini 3 Flash 22.8% Launch baseline Dec 2025 Official leaderboard
5 Claude Sonnet 4.6 21.6% Launch baseline Feb 2026 Official leaderboard

Number one over time

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

Anthropic
Own leaderboard Not tested since Apr 2026
Claude Opus 4.6 33%

Source: Official Toloka Arena leaderboard

Scores over time

All the scores we have, one dot each, so a model tested at several settings appears more than once.

On the benchmark’s own leaderboard Best so far
0% 20% 40% 60% 80% 100% 2026 Near the ceiling (85%) Claude Opus 4.6 Gemini 3 Flash 0% 20% 40% 60% 80% 100% 2026 Near the ceiling (85%) Claude Opus 4.6 Gemini 3 Flash

Source: Official Toloka Arena leaderboard

No lab model card reports it yet

We read the headline results of 522 launch posts from 52 labs, and none of them list this benchmark.

More in Tool use

All 144 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 Carbon 53.9%
  • 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%