热度8.9▼ 0.6
overall
bfcl / accuracy · 109 行结果
| 排名 | 模型 | 子项 | 分数 | Metric | 时间 |
|---|---|---|---|---|---|
| #1 | Claude-Opus-4-5-20251101 (FC) Anthropic | overall bfcl | 77.5% | accuracy | 2026-08-28 |
| #2 | Claude-Sonnet-4-5-20250929 (FC) Anthropic | overall bfcl | 73.2% | accuracy | 2026-08-28 |
| #3 | Gemini-3-Pro-Preview (Prompt) Google | overall bfcl | 72.5% | accuracy | 2026-08-28 |
| #4 | GLM-4.6 (FC thinking) Zhipu AI | overall bfcl | 72.4% | accuracy | 2026-08-28 |
| #5 | Grok-4-1-fast-reasoning (FC) xAI | overall bfcl | 69.6% | accuracy | 2026-08-28 |
| #6 | Claude-Haiku-4-5-20251001 (FC) Anthropic | overall bfcl | 68.7% | accuracy | 2026-08-28 |
| #7 | Gemini-3-Pro-Preview (FC) Google | overall bfcl | 68.1% | accuracy | 2026-08-28 |
| #8 | o3-2025-04-16 (Prompt) OpenAI | overall bfcl | 63.1% | accuracy | 2026-08-28 |
| #9 | Grok-4-0709 (Prompt) xAI | overall bfcl | 63% | accuracy | 2026-08-28 |
| #10 | Grok-4-0709 (FC) xAI | overall bfcl | 61.4% | accuracy | 2026-08-28 |
| #11 | Moonshotai-Kimi-K2-Instruct (FC) MoonshotAI | overall bfcl | 59.1% | accuracy | 2026-08-28 |
| #12 | Grok-4-1-fast-non-reasoning (FC) xAI | overall bfcl | 58.3% | accuracy | 2026-08-28 |
| #13 | Command A Reasoning (FC) Cohere | overall bfcl | 57.1% | accuracy | 2026-08-28 |
| #14 | DeepSeek-V3.2-Exp (Prompt + Thinking) DeepSeek | overall bfcl | 56.7% | accuracy | 2026-08-28 |
| #15 | Gemini-2.5-Flash (FC) Google | overall bfcl | 56.2% | accuracy | 2026-08-28 |
| #16 | GPT-5.2-2025-12-11 (FC) OpenAI | overall bfcl | 55.9% | accuracy | 2026-08-28 |
| #17 | GPT-5-mini-2025-08-07 (FC) OpenAI | overall bfcl | 55.5% | accuracy | 2026-08-28 |
| #18 | xLAM-2-32b-fc-r (FC) Salesforce | overall bfcl | 54.7% | accuracy | 2026-08-28 |
| #19 | DeepSeek-V3.2-Exp (FC) DeepSeek | overall bfcl | 54.1% | accuracy | 2026-08-28 |
| #20 | GPT-4.1-2025-04-14 (FC) OpenAI | overall bfcl | 54% | accuracy | 2026-08-28 |
| #21 | o4-mini-2025-04-16 (FC) OpenAI | overall bfcl | 53.2% | accuracy | 2026-08-28 |
| #22 | xLAM-2-70b-fc-r (FC) Salesforce | overall bfcl | 53.1% | accuracy | 2026-08-28 |
| #23 | Qwen3-235B-A22B-Instruct-2507 (Prompt) Qwen | overall bfcl | 52.2% | accuracy | 2026-08-28 |
| #24 | GPT-5-nano-2025-08-07 (FC) OpenAI | overall bfcl | 51.5% | accuracy | 2026-08-28 |
| #25 | Nanbeige4-3B-Thinking-2511 (FC) Nanbeige | overall bfcl | 51.4% | accuracy | 2026-08-28 |
109 条结果 · 当前 1-25
1 / 5