Toolathlon Verified
Toolathlon Verified - agentic tool use benchmark. Pass@1 score.
Category
General Agents
Max Score
—
Score Type
percent
Active
Yes
Model Scores
Scores for Toolathlon Verified
| Model | Score | Date | Verified |
|---|---|---|---|
| Fable-5 |
100.00%
|
18.08.2026 | Unverified |
| GPT-5.6 Sol |
94.01%
|
18.08.2026 | Unverified |
| Claude Opus 4.8 |
96.61%
|
18.08.2026 | Unverified |
| Qwen3.7-Max |
43.71%
|
18.08.2026 | Unverified |
| Qwen3.8-2.4T-A95B |
89.22%
|
18.08.2026 | Verified |
| Kimi K3 |
97.21%
|
18.08.2026 | Verified |
| DeepSeek-V4-Flash-0731 |
84.83%
|
31.07.2026 | Verified |
| GLM-5.2 |
64.07%
|
31.07.2026 | Verified |
| Opus-4.8 |
96.61%
|
31.07.2026 | Verified |
| DeepSeek-V4-Flash |
39.92%
|
26.06.2026 | Verified |
| Ornith-1.5-35B-A3B |
41.72%
|
19.08.2026 | Verified |
| Ornith-1.0-35B-A3B |
29.14%
|
19.08.2026 | Unverified |
| Qwen3.6-35B-A3B |
27.74%
|
19.08.2026 | Unverified |
| Gemma-4-31B |
25.95%
|
19.08.2026 | Unverified |
| Qwen3.5-397B-A17B |
20.96%
|
19.08.2026 | Unverified |
| Kimi K2.6 |
44.31%
|
23.08.2026 | Verified |
| GPT-5.4 |
53.49%
|
23.08.2026 | Verified |
| Claude Opus 4.6 |
38.72%
|
23.08.2026 | Verified |
| Gemini 3.1 Pro |
41.92%
|
23.08.2026 | Verified |
| Kimi K2.5 |
27.80
|
23.08.2026 | Verified |
| DeepSeek-V4-Pro |
47.90%
|
26.06.2026 | Verified |
| DeepSeek-V4-Pro-0813 |
92.42%
|
13.08.2026 | Verified |
| Opus-4.6 |
38.72%
|
26.06.2026 | Verified |
| GLM-5.1 |
25.75%
|
26.06.2026 | Verified |
| Qwen3.8-Flash-Next |
91.22%
|
26.08.2026 | Verified |
| Qwen3.8-27B |
78.44%
|
26.08.2026 | Unverified |
| Qwen3.7-Plus |
45.51%
|
26.08.2026 | Unverified |
| GLM-5.3 |
90.22%
|
28.08.2026 | Verified |
| Hy3 |
56.69%
|
28.08.2026 | Verified |
| Hy4 preview |
92.42%
|
28.08.2026 | Verified |
| DeepSeek V4 Pro |
92.42%
|
28.08.2026 | Verified |
| Claude Opus 5 |
97.21%
|
28.08.2026 | Verified |
| DeepSeek-V4-Flash-Vision-Exp |
96.01%
|
08.09.2026 | Verified |