Agent-Diff
Agents use code to complete tasks across replicas of Slack, Linear, Box, and Calendar. The evaluator compares the resulting application state with the expected changes.
In February 2026, DeepSeek V3.2 led nine models with an overall score of 88.1. The table also reports Gemini 3 Flash, GPT-OSS 120B, and Claude Haiku 4.5.
- Released
- February 2026
- Kind
- Apps and MCP servers
- Level
- University
- Scored
- Checked automatically
- Answers
- Agent task
- Tasks
- All public
- Measures
- Capability
- Language
- English
- Interaction
- Agentic
- Environment
- APIs and tools
- Items from
- Generated
- Refresh
- One fixed set
- Run by
- Anyone
- In views
- Agents
- Strongest model tested
-
Gemini 3 Flash #60 on the capability index
- Last model added
- December 2025
- Scores refreshed
- November 20th, 2026
DeepSeek-V3.2 leads with 88.1% among models released by December 2025 DeepSeek-V3.2 leads with 88.1% 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. 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:
- GPT-6.2 Astra
- Claude Fable 5.2
-
Gemini 4 Carbon
- GPT-6 Astra
- and 16 more
- 1
DeepSeek-V3.2 No documentation 88.1%
- 2
Devstral 2 No documentation 86%
- 3 qwen3-vl-235b (model ID disputed) No documentation 79.2%
- 4 Kimi K2 Sep 2025, No documentation 75.4%
- 5 Grok 4.1 Fast No documentation 74.9%
- 6
Gemini 3 Flash No documentation 73.8%
- 7 gpt-oss-120b No documentation 68.5%
- 8 Claude Haiku 4.5 No documentation 49.3%
- 9
Llama 4 Scout No documentation 38%
Source: The Agent-Diff paper
- 1
DeepSeek-V3.2 No documentation 88.1%
- 2
Devstral 2 No documentation 86%
- 3 Kimi K2 Sep 2025, No documentation 75.4%
- 4 Grok 4.1 Fast No documentation 74.9%
- 5
Gemini 3 Flash No documentation 73.8%
- 6 gpt-oss-120b No documentation 68.5%
- 7 Claude Haiku 4.5 No documentation 49.3%
- 8
Llama 4 Scout No documentation 38%
Source: The Agent-Diff paper
| # | Entry | Score ± | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | | 88.1% ±2.4 | No documentation | Dec 2025 | Official leaderboard |
| 2 | | 86% ±3.1 | No documentation | Dec 2025 | Official leaderboard |
| 3 | qwen3-vl-235b (model ID disputed) | 79.2% ±3.3 | No documentation | Official leaderboard | |
| 4 | Kimi K2 Sep 2025 | 75.4% ±3.5 | No documentation | Sep 2025 | Official leaderboard |
| 5 | Grok 4.1 Fast | 74.9% ±2.7 | No documentation | Nov 2025 | Official leaderboard |
| 6 | | 73.8% ±3.7 | No documentation | Dec 2025 | Official leaderboard |
| 7 | gpt-oss-120b | 68.5% ±4.1 | No documentation | Aug 2025 | Official leaderboard |
| 8 | Claude Haiku 4.5 | 49.3% ±5.5 | No documentation | Oct 2025 | Official leaderboard |
| 9 | | 38% ±4.1 | No documentation | Apr 2025 | Official leaderboard |
| # | Model | Score ± | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | | 88.1% ±2.4 | No documentation | Dec 2025 | Official leaderboard |
| 2 | | 86% ±3.1 | No documentation | Dec 2025 | Official leaderboard |
| 3 | Kimi K2 Sep 2025 | 75.4% ±3.5 | No documentation | Sep 2025 | Official leaderboard |
| 4 | Grok 4.1 Fast | 74.9% ±2.7 | No documentation | Nov 2025 | Official leaderboard |
| 5 | | 73.8% ±3.7 | No documentation | Dec 2025 | Official leaderboard |
| 6 | gpt-oss-120b | 68.5% ±4.1 | No documentation | Aug 2025 | Official leaderboard |
| 7 | Claude Haiku 4.5 | 49.3% ±5.5 | No documentation | Oct 2025 | Official leaderboard |
| 8 | | 38% ±4.1 | No documentation | Apr 2025 | Official leaderboard |
Rankings by part
We read 4 parts from the benchmark’s paper, each ranking models on one part of the test, such as Box, Calendar and Linear. DeepSeek-V3.2 leads 3 of them, and Gemini 3 Flash leads the other one. Arrows show how far a model moved from its overall rank among the models we track.
Box
8 models we track have a score here.
- 1
Gemini 3 Flash ↑4 80.3%
- 2
Devstral 2 79%
- 3
DeepSeek-V3.2 ↓2 76.6%
- 4 gpt-oss-120b ↑2 70.1%
- 5 Kimi K2 Sep 2025 ↓2 66.5%
- 6 Grok 4.1 Fast ↓2 58.5%
- 7 Claude Haiku 4.5 45.1%
- 8
Llama 4 Scout 33.7%
Calendar
8 models we track have a score here.
- 1
DeepSeek-V3.2 87.5%
- 2
Devstral 2 80%
- 3 Grok 4.1 Fast ↑1 75.7%
- 4 Kimi K2 Sep 2025 ↓1 72.3%
- 5 gpt-oss-120b ↑1 68.4%
- 6
Gemini 3 Flash ↓1 62.2%
- 7 Claude Haiku 4.5 57.8%
- 8
Llama 4 Scout 41.4%
Linear
8 models we track have a score here.
- 1
DeepSeek-V3.2 94.8%
- 2
Devstral 2 91.5%
- 3 Kimi K2 Sep 2025 88.2%
- 4
Gemini 3 Flash ↑1 84%
- 5 gpt-oss-120b ↑1 79.5%
- 6 Grok 4.1 Fast ↓2 66%
- 7 Claude Haiku 4.5 35.6%
- 8
Llama 4 Scout 20.9%
Slack
8 models we track have a score here.
- 1
DeepSeek-V3.2 86.1%
- 2
Devstral 2 85.7%
- 3 Kimi K2 Sep 2025 82.2%
- 4
Gemini 3 Flash ↑1 77.5%
- 5 Grok 4.1 Fast ↓1 77.1%
- 6 gpt-oss-120b 69.1%
- 7 Claude Haiku 4.5 57.3%
- 8
Llama 4 Scout 42.9%
The best score, 88.1%, costs $0.03 a task
Runs on the cost frontier score higher than any run that's cheaper. The costs are the leaderboard's own estimates, so compare them only within this benchmark.
Source: The Agent-Diff paper
| Model | Effort | Harness | Score | Cost per task | Output tokens |
|---|---|---|---|---|---|
| No documentation | 88.1% | $0.03 | |||
| No documentation | 86% | $0.08 | |||
| Kimi K2 Sep 2025 | No documentation | 75.4% | $0.04 | ||
| Grok 4.1 Fast | No documentation | 74.9% | $0.01 | ||
| No documentation | 73.8% | $0.05 | |||
| gpt-oss-120b | No documentation | 68.5% | $0.02 | ||
| Claude Haiku 4.5 | No documentation | 49.3% | $0.22 | ||
| No documentation | 38% | $0.02 |
The best score, 88.1%, costs $0.03 a task
Runs on the cost frontier score higher than any run that's cheaper. The costs are the leaderboard's own estimates, so compare them only within this benchmark.
Source: The Agent-Diff paper
| Model | Effort | Harness | Score | Cost per task | Output tokens |
|---|---|---|---|---|---|
| No documentation | 88.1% | $0.03 | |||
| No documentation | 86% | $0.08 | |||
| Kimi K2 Sep 2025 | No documentation | 75.4% | $0.04 | ||
| Grok 4.1 Fast | No documentation | 74.9% | $0.01 | ||
| No documentation | 73.8% | $0.05 | |||
| gpt-oss-120b | No documentation | 68.5% | $0.02 | ||
| Claude Haiku 4.5 | No documentation | 49.3% | $0.22 | ||
| No documentation | 38% | $0.02 |
Number one over time
Lab claims count from the day the card came out, independent runs from the model’s release.
Source: The Agent-Diff paper
DeepSeek-V3.2 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.
Source: Official Agent-Diff 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
- 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 (9 entries).
- Pass Models scored 8 models we track, plus 1 other entry on its leaderboard.
- Note Newest score The newest came 11 months ago, in December 2025, for Gemini 3 Flash. That’s expected for a saturated test.
- Note Frontier models None of the top 10 has a score, which is fine for a retired test. The strongest tested is Gemini 3 Flash (#60).
- Note Headroom Saturated. The best is 88.1%, past 85% since December 2025.
Leaderboard import 3 pass
- Pass Importer We read the board on arxiv.org: 8 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.