Agentic benchmark
Toolathlon-Verified leaderboard
Every model the catalog carries a published Toolathlon-Verified value for, ranked by that value.
CategoryAgentic
MeasureInteractive tool-use score
TasksVerified multi-tool workflows
DifficultyAdvanced tool use
Published byKimi K3: Open Frontier Intelligence
A verified tool-use benchmark variant for completing multi-step workflows with external tools.
Toolathlon-Verified ranking
16 models with a published Toolathlon-Verified value, ordered by that value, highest first. Models the source has not scored on this benchmark are not listed — they are unmeasured, not last.
| Rank | Model | Provider | Interactive tool-use score |
|---|---|---|---|
| 1 |  Claude Opus 5 | Anthropic | 80.6 |
| 2 |  GLM-5.3-Flash | Z.AI | 78.4 |
| 3 | Claude Fable 5.1 | Anthropic | 77.8 |
| 4 |  DeepSeek V4 Pro 0813 | DeepSeek | 74.1 |
| 4 |  Hy4 preview | Tencent | 74.1 |
| 6 |  Qwen3.8-Flash-Next | Alibaba | 73.5 |
| 7 |  Kimi K3 | Moonshot AI | 73.2 |
| 8 | GLM-5.3 | Z.AI | 73.0 |
| 9 | Qwen3.8 Max | Alibaba | 72.5 |
| 10 | OAOrnith-1.5-397B | Ornith AI | 71.2 |
| 11 | DeepSeek V4 Flash 0731 | DeepSeek | 70.3 |
| 12 | DSdots3-note Preview | Dots Studio | 55.6 |
| 13 | TMInkling-Small | Thinking Machines Lab | 54.4 |
| 14 |  Laguna S 2.1 | Poolside | 49.7 |
| 15 | OAOrnith-1.5-35B-A3B | Ornith AI | 48.7 |
| 16 | OAOrnith-1.5-9B | Ornith AI | 41.2 |
Evidence key: Observed
Rows are ordered by the value Kimi K3: Open Frontier Intelligence published, highest first. The source does not state whether a higher value is the better result, so this page does not either: for a benchmark that measures a rate of failure, read the table from the bottom.