Best for agents and tools
GPT-5.6 Sol and Muse Spark 1.1 tie for the lead · 3 fresh boards · counts toward the leader of leaders · Calling functions and tools, using MCP servers, searching the web.
12 of 12 models
| # | Model | Score#1s | ||
|---|---|---|---|---|
| 1 |  GPT-5.6 SolOpenAItop 10 on 1, #1 on 1 | 33.3 | 33.31 | 1 |
| 1 |  Muse Spark 1.1Metatop 10 on 1, #1 on 1 | 33.3 | 33.31 | 1 |
| 3 |  Claude Opus 4.5Anthropictop 10 on 1, #1 on 1 | 33.3 | 33.31 | 1 |
| 4 | Claude Fable 5Anthropictop 10 on 2 | 33.3 | 33.30 | 2 |
| 5 | Claude Fable 5.1Anthropictop 10 on 1 | 30.0 | 30.00 | 1 |
| 6 | Claude Opus 4.6Anthropictop 10 on 1 | 30.0 | 30.00 | 1 |
| 7 | Claude Sonnet 4.5Anthropictop 10 on 1 | 30.0 | 30.00 | 1 |
| 8 | Claude Opus 5Anthropictop 10 on 1 | 26.7 | 26.70 | 1 |
| 9 | GPT-5.5OpenAItop 10 on 1 | 26.7 | 26.70 | 1 |
| 10 |  Gemini 3 ProGoogletop 10 on 1 | 26.7 | 26.70 | 1 |
| 11 |  GLM 4.6Z.ai (Zhipu)top 10 on 1 | 23.3 | 23.30 | 1 |
| 11 |  Qwen3.8 2.4T A95BAlibabatop 10 on 1 | 23.3 | 23.30 | 1 |
Boards
| Board | Score | ||
|---|---|---|---|
 BFCLUC Berkeley Gorilla#1 Claude Opus 4.5 | Claude Opus 4.5 | 77.5% | Apr 12, 2026 |
 MCP AtlasScale AI#1 Muse Spark 1.1 | Muse Spark 1.1 | 88.1% | Sep 23, 2026 |
 Search ArenaLMArena#1 GPT-5.6 Sol | GPT-5.6 Sol | 1,257 | Aug 24, 2026 |
The wall
| Agents and tools | |||
|---|---|---|---|
| Model · podium score | BFCL | MCP Atlas | Search Arena |
| 1GPT-5.6 Sol33.3 | |||
| 1Muse Spark 1.133.3 | |||
| 3Claude Opus 4.533.3 | |||
| 4Claude Fable 533.3 | |||
| 5Claude Fable 5.130.0 | |||
| 6Claude Opus 4.630.0 | |||
| 7Claude Sonnet 4.530.0 | |||
| 8Claude Opus 526.7 | |||
| 9GPT-5.526.7 | |||
| 10Gemini 3 Pro26.7 | |||
#1 with the vendor’s logo23 podium7 top 10 stale board, not countedArrow keys move, Enter opens
Rank over time
Sources: each leaderboard's own published results page, captured every day at 04:30 UTC. Scores exactly as each board published them; we run no evaluations. Logos via logo.dev; trademarks belong to their owners.