Benchmark Almanac

Small Model Agent Bench

Qwen3-Coder-480B-A35B 95.7% leads since August 2026
Not in model cards

Models choose tools and supply their arguments in 28 Chinese and English episodes. Fixed tool responses let the grader check planning, recovery, and task completion.

Kaggle publishes scores for 5 distinct model versions.

Made by
Cacinie
Released
August 2026
Kind
Function calling
Level
School
Scored
Checked automatically
Answers
Agent task
Tasks
All public
Measures
Capability
Language
Chinese, English
In and out
Text → Actions, Text
Interaction
Agentic
Environment
APIs and tools
Refresh
One fixed set
Run by
Anyone
In views
Agents
Strongest model tested
Gemini 3.8 Flash #24 on the capability index
Last model added
September 2026
Scores refreshed
November 20th, 2026
5
Entries on its own leaderboard, 4 models we track

Qwen3-Coder-480B-A35B leads with 95.7% among models released by September 2026 Qwen3-Coder-480B-A35B leads with 95.7% among models released by September 2026

Best score per entry from the benchmark's own leaderboard, read on November 20th, 2026. Where a model ran with several settings or harnesses, we keep its best. 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 September 2026, and nobody has tested a newer one. Among the 20 highest-ranked models on the capability index, these have no score yet:

  1. 1 Qwen3-Coder-480B-A35B 95.7%
  2. 2 Gemini 3.8 Flash 95.6%
  3. 3 Qwen 3 235B A22B Instruct 2506 93.9%
  4. 4 Gemma 4 26B A4B 91.5%
  5. 5 gpt-oss-20b 90.4%

Source: Official Small Model Agent Bench leaderboard

#EntryScoreSettingReleasedRun onSource
1 Qwen3-Coder-480B-A35B 95.7% Jul 2025 Oct 2026 Official leaderboard
2 Gemini 3.8 Flash 95.6% Sep 2026 Oct 2026 Official leaderboard
3 Qwen 3 235B A22B Instruct 2506 93.9% Oct 2026 Official leaderboard
4 Gemma 4 26B A4B 91.5% Apr 2026 Oct 2026 Official leaderboard
5 gpt-oss-20b 90.4% Aug 2025 Oct 2026 Official leaderboard
#ModelScoreSettingReleasedRun onSource
1 Qwen3-Coder-480B-A35B 95.7% Jul 2025 Oct 2026 Official leaderboard
2 Gemini 3.8 Flash 95.6% Sep 2026 Oct 2026 Official leaderboard
3 Gemma 4 26B A4B 91.5% Apr 2026 Oct 2026 Official leaderboard
4 gpt-oss-20b 90.4% Aug 2025 Oct 2026 Official leaderboard

Number one over time

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

Qwen
Own leaderboard Passed 85% in Aug 2026, by Qwen3-Coder-480B-A35B

Source: Official Small Model Agent Bench leaderboard

Qwen3-Coder-480B-A35B on the official leaderboard passed 85% in July 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
On the benchmark’s own leaderboard
0% 20% 40% 60% 80% 100% 2026 Near the ceiling (85%) Qwen3-Coder-480B-A35B 0% 20% 40% 60% 80% 100% 2026 Near the ceiling (85%) Qwen3-Coder-480B-A35B

Source: Official Small Model Agent 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.

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 9 checks pass. Every benchmark

Catalog record 2 pass
  • Pass Task access All tasks are public.
  • Pass Confidence Checked against a primary source.
Scores 3 pass 2 notes
  • Pass Independent runs Scores from the official leaderboard (5 entries).
  • Pass Models scored 4 models we track, plus 1 other entry on its leaderboard.
  • Pass Newest score The newest is from September 2026, for Gemini 3.8 Flash.
  • Note Frontier models None of the top 10 has a score, which is fine for a retired test. The strongest tested is Gemini 3.8 Flash (#24).
  • Note Headroom Saturated. The best is 95.7%, past 85% since July 2025.
Leaderboard import 3 pass
  • Pass Importer We read the board on kaggle.com: 4 rows for models we track and 1 other entry 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