Benchmark Almanac

BotChat

GPT-4 Jun 2023 73.2 leads since October 2023
Not in model cards

Two instances of a model sustain a conversation. Judges assess the resulting dialogue.

Released
October 2023
Kind
Multi-turn conversation
Level
Everyday
Scored
Graded by a model
Answers
Open-ended
Tasks
All public
Measures
Capability
Language
English
In and out
Text → Text
Interaction
Multi-agent
Items from
Real work and use
Refresh
One fixed set
Run by
Anyone
In views
Agents
Strongest model tested
GPT-4 Jun 2023 #186 on the capability index
Last model added
September 2023
Scores refreshed
November 20th, 2026
14
Entries on its own leaderboard, 10 models we track

GPT-4 leads with 73.2 among models released by September 2023 GPT-4 leads with 73.2 among models released by September 2023

Best score per entry from the benchmark's own leaderboard, read on November 20th, 2026. 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. This view shows only models we track, each at its best.

The newest model with a score here came out in September 2023, and nobody has tested a newer one. Among the 20 highest-ranked models on the capability index, these have no score yet:

  1. 1 GPT-4 Jun 2023 73.2
  2. 2 Vicuna-13B 68.0
  3. 3 Qwen-14B 67.1
  4. 4 internlm-chat-20b 64.2
  5. 5 Vicuna-7B 55.6
  6. 6 Qwen-7B-Chat 54.1
  7. 7 Baichuan2-13B-Chat 47.1
  8. 8 InternLM-7B-Chat 46.6
  9. 9 GPT-3.5 Turbo Jun 2023 35.8
  10. 10 chatglm2-6b 33.8
  11. 11 Claude 2 21.4
  12. 12 Llama 2-7B 12.4
  13. 13 Llama 2-70B 11.3
  14. 14 Llama 2-13B 10.6

Source: Official BotChat leaderboard

#EntryScoreSettingDateLinkSource
1 GPT-4 Jun 2023 73.2 Jun 2023 Official leaderboard
2 Vicuna-13B 68.0 huggingface.co Official leaderboard
3 Qwen-14B 67.1 Sep 2023 huggingface.co Official leaderboard
4 internlm-chat-20b 64.2 Sep 2023 huggingface.co Official leaderboard
5 Vicuna-7B 55.6 huggingface.co Official leaderboard
6 Qwen-7B-Chat 54.1 huggingface.co Official leaderboard
7 Baichuan2-13B-Chat 47.1 Sep 2023 huggingface.co Official leaderboard
8 InternLM-7B-Chat 46.6 huggingface.co Official leaderboard
9 GPT-3.5 Turbo Jun 2023 35.8 Jun 2023 Official leaderboard
10 chatglm2-6b 33.8 Jun 2023 huggingface.co Official leaderboard
11 Claude 2 21.4 Jul 2023 Official leaderboard
12 Llama 2-7B 12.4 Jul 2023 ai.meta.com Official leaderboard
13 Llama 2-70B 11.3 Jul 2023 ai.meta.com Official leaderboard
14 Llama 2-13B 10.6 Jul 2023 ai.meta.com Official leaderboard
#ModelScoreSettingDateLinkSource
1 GPT-4 Jun 2023 73.2 Jun 2023 Official leaderboard
2 Qwen-14B 67.1 Sep 2023 huggingface.co Official leaderboard
3 internlm-chat-20b 64.2 Sep 2023 huggingface.co Official leaderboard
4 Baichuan2-13B-Chat 47.1 Sep 2023 huggingface.co Official leaderboard
5 GPT-3.5 Turbo Jun 2023 35.8 Jun 2023 Official leaderboard
6 chatglm2-6b 33.8 Jun 2023 huggingface.co Official leaderboard
7 Claude 2 21.4 Jul 2023 Official leaderboard
8 Llama 2-7B 12.4 Jul 2023 ai.meta.com Official leaderboard
9 Llama 2-70B 11.3 Jul 2023 ai.meta.com Official leaderboard
10 Llama 2-13B 10.6 Jul 2023 ai.meta.com Official leaderboard

Number one over time

Lab claims count from the day the card came out, independent runs from the model’s release.

OpenAI
Own leaderboard Not tested since Oct 2023
GPT-4 73.2

Source: Official BotChat leaderboard

Scores over time

All the scores we have, one dot each, so a model tested at several settings appears more than once.

Plot with other benchmarks
On the benchmark’s own leaderboard
0.00 20.0 40.0 60.0 80.0 2023 0.00 20.0 40.0 60.0 80.0 2023

Source: Official BotChat 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

All 144 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

8 of 9 checks pass, 1 warning. Look first at the Newest score check. The newest came 3 years ago, in September 2023, for Qwen-14B. Every benchmark

Catalog record 2 pass
  • Pass Task access All tasks are public.
  • Pass Confidence Checked against a primary source.
Scores 1 warning 2 pass 2 notes
  • Pass Independent runs Scores from the official leaderboard (14 entries).
  • Pass Models scored 10 models we track, plus 4 other entries on its leaderboard.
  • Warning Newest score The newest came 3 years ago, in September 2023, for Qwen-14B.
  • Note Frontier models None of the top 10 has a score. The strongest tested is GPT-4 (#186).
  • Note Headroom Scored as a plain number, with no fixed ceiling.
Leaderboard import 3 pass
  • Pass Importer We read the board on open-compass.github.io: 10 rows for models we track and 4 other entries at the last read.
  • Pass Last read November 20th, 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.

How we check