OutboundEval
Agents conduct outbound calls with simulated users. The benchmark scores compliance with the professional workflow and the quality of the interaction.
The authors publish scores for 12 models, including separate task flow and interaction scores. The evaluation combines automated checks with human review.
- Made by
- Meituan with xbench and Agora
- Released
- October 2025
- Kind
- Multi-turn conversation
- Level
- Expert
- Scored
- Graded by a model
- Answers
- Agent task
- Tasks
- All public
- Measures
- Capability
- Language
- English
- Interaction
- Multi-agent
- Environment
- APIs and tools
- Items from
- Generated
- Refresh
- One fixed set
- Run by
- Anyone
- In views
- Agents, Audio and speech
doubao-1.5-32k (ByteDance, 2025) tops the leaderboard with 0.89
Best score per entry from the benchmark's paper, read on November 21st, 2026. A paper’s table doesn’t add newer models. Where a model ran with several settings or harnesses, we keep its best. Names in gray aren't in our model list: fine-tunes, agent systems, products and older models. They don't count toward leaders.
- 0.89 doubao-1.5-32k (ByteDance, 2025)
- 0.88 gpt-4.1 (OpenAI, 2025)
- 0.87 claude-4-sonnet (Anthropic, 2025b)
- 0.87 gemini-2.5-flash (Comanici et al., 2025)
- 0.87 qwen3-32b-base (Yang et al., 2025)
- 0.86 gpt-4o (OpenAI, 2024)
- 0.84 claude-3.5-sonnet (Anthropic, 2024)
- 0.84 gemini-2.5-pro (Comanici et al., 2025)
- 0.82 deepseek-v3 (DeepSeek-AI et al., 2025b)
- 0.82 claude-3.7-sonnet (Anthropic, 2025a)
- 0.80 deepseek-r1 (DeepSeek-AI et al., 2025a)
- 0.79 kimi-k2-instruct (Kimi-Team et al., 2025)
- 1 doubao-1.5-32k (ByteDance, 2025) 0.89
- 2 gpt-4.1 (OpenAI, 2025) 0.88
- 3 claude-4-sonnet (Anthropic, 2025b) 0.87
- 4 gemini-2.5-flash (Comanici et al., 2025) 0.87
- 5 qwen3-32b-base (Yang et al., 2025) 0.87
- 6 gpt-4o (OpenAI, 2024) 0.86
- 7 claude-3.5-sonnet (Anthropic, 2024) 0.84
- 8 gemini-2.5-pro (Comanici et al., 2025) 0.84
- 9 deepseek-v3 (DeepSeek-AI et al., 2025b) 0.82
- 10 claude-3.7-sonnet (Anthropic, 2025a) 0.82
- 11 deepseek-r1 (DeepSeek-AI et al., 2025a) 0.80
- 12 kimi-k2-instruct (Kimi-Team et al., 2025) 0.79
Source: The OutboundEval paper
| # | Entry | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | doubao-1.5-32k (ByteDance, 2025) | 0.89 | Official leaderboard | ||
| 2 | gpt-4.1 (OpenAI, 2025) | 0.88 | Official leaderboard | ||
| 3 | claude-4-sonnet (Anthropic, 2025b) | 0.87 | Official leaderboard | ||
| 4 | gemini-2.5-flash (Comanici et al., 2025) | 0.87 | Official leaderboard | ||
| 5 | qwen3-32b-base (Yang et al., 2025) | 0.87 | Official leaderboard | ||
| 6 | gpt-4o (OpenAI, 2024) | 0.86 | Official leaderboard | ||
| 7 | claude-3.5-sonnet (Anthropic, 2024) | 0.84 | Official leaderboard | ||
| 8 | gemini-2.5-pro (Comanici et al., 2025) | 0.84 | Official leaderboard | ||
| 9 | deepseek-v3 (DeepSeek-AI et al., 2025b) | 0.82 | Official leaderboard | ||
| 10 | claude-3.7-sonnet (Anthropic, 2025a) | 0.82 | Official leaderboard | ||
| 11 | deepseek-r1 (DeepSeek-AI et al., 2025a) | 0.80 | Official leaderboard | ||
| 12 | kimi-k2-instruct (Kimi-Team et al., 2025) | 0.79 | Official 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 Instructions and chat
- IFEval In use Models answer about 500 prompts containing verifiable instructions such as word limits or required keywords. Code checks each instruction for strict and loose accuracy.
Gemma 4 31B IT 98.9%
- IFBench In use 58 new out-of-domain verifiable output constraints. Scored by programmatic constraint checks (strict or loose). Flint 89.2%
- MultiChallenge In use Multi-turn conversations testing instruction retention, inference memory, versioned editing and self-coherence. Graded by LLM judge with rubrics. GPT-6.1 Sol 82%
- Multi-IF In use Models follow verifiable instructions over three-turn conversations in eight languages, extending IFEval. Scored by instruction accuracy at each turn. LFM3-1.7B 89.1%
- AdvancedIF In use Models respond to over 1,600 prompts with complex, multi-turn, and system-level instructions. A judge model checks each response against expert-written rubrics.
MAI-Thinking-1 85%
- MM-IFEval In use Multimodal models follow image-grounded instructions with exact output constraints. Checks mix rule-based verification and a judge model. GPT-4o 64.6%
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 (12 entries).
- Pass Models scored 12 entries on its leaderboard, none a model we track.
- Note Newest score No scores yet.
- Note Frontier models No models scored yet.
- Note Headroom Scored as a plain number, with no fixed ceiling.
Leaderboard import 3 pass
- Pass Importer We read the board on github.com: 12 entries at the last read, none a model we track.
- Pass Last read November 21st, 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.