RuLES 2.0
Version 2.0
Models follow explicit rules while talking with a user. Each scenario checks automatically whether the model broke a rule.
The authors added test cases in March 2024. Their repository has 259 GitHub stars.
- Made by
- Norman Mu and collaborators
- Released
- March 2024
- Kind
- Following precise instructions
- Level
- Everyday
- Scored
- Checked automatically
- Answers
- Agent task
- Tasks
- All public
- Measures
- Propensity
- Behavior
- Misaligned with intent
- Language
- English
- Interaction
- Multi-turn
- Items from
- Generated
- Refresh
- New versions replace it
- Run by
- Anyone
- Based on
- RuLES
- Strongest model tested
- Claude 3 Opus #173 on the capability index
- Last model added
- February 2024
- Scores refreshed
- November 21st, 2026
GPT-4 Turbo leads with 9.54% among models released by February 2024 GPT-4 Turbo leads with 9.54% among models released by February 2024
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. Every run is in the next chart. 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 February 2024, and nobody has tested a newer one. Among the 20 highest-ranked models on the capability index, these have no score yet:
- GPT-6.2 Astra
- Claude Fable 5.2
-
Gemini 4 Carbon
- GPT-6 Astra
- and 16 more
- 9.54 GPT-4 Turbo
- 9.53 GPT-4 Turbo (Jan 2024)
- 8.51 Claude 3 Opus
- 8.30 GPT-3.5 Turbo
- 7.90 GPT-3.5 Turbo
- 7.88 claude-instant-v1.2
- 7.02
Qwen1.5-72B
- 6.87 Claude 2.1
- 6.86 Yi-34B-200K-AEZAKMI-v2
- 6.80 GPT-3.5 Turbo
- 6.79 Claude 2
- 6.76 tulu-2-70b
- 6.64 dolphin-2.2-70b
- 6.51
Gemini 1.0 Pro
- 6.50 Mixtral-SlimOrca-8x7B
- 6.49 Instruct_Mixtral-8x7B-v0.1_Dol[..]
- 6.40 Nous-Hermes-2-Yi-34B
- 6.39
DeepSeek LLM 67B
- 6.39 Claude 3 Sonnet
- 6.38 dolphin-2.2-yi-34b-200k
- 6.38 Yi-34B-AEZAKMI-v1
- 6.30 yi-34B-v2
- 6.25 Nous-Hermes-2-Mixtral-8x7B-SFT
- 6.24 yi-34B-v3
- 6.15 OrionStar-Yi-34B-Chat
- 6.13 blossom-v4-yi-34b
- 6.12 deepseek-llm-67b-base
- 6.11 Llama-2-7b-hf
- 6.08 Yi-34B-200K-DARE-merge-v5
- 6.06 Capybara-Tess-Yi-34B-200K
- 6.03 platypus-yi-34b
- 5.99 openchat-3.5-0106
- 5.96 notux-8x7b-v1
- 5.96 orca_mini_v3_13b
- 5.94 SOLAR-0-70b-16bit
- 5.92 Mistral-7B-AEZAKMI-v2
- 5.87 samantha-mistral-7b
- 5.79
Gemma 7B
- 5.78 GPT-3.5 Turbo (Mar 2023)
- 5.76 vicuna-7b-v1.5
- 5.74 openchat-3.5-1210
- 5.73 dolphin-2.6-mixtral-8x7b
- 5.73 neural-chat-7b-v3-2
- 5.69 blossom-v3-mistral-7b
- 5.69 tulu-2-13b
- 5.66 dolphin-2.2.1-mistral-7b
- 5.64 CaPlatTessDolXaBoros-Yi-34B-20[..]
- 5.63 orca_mini_v3_70b
- 5.63
Mistral 7B v0.1
- 5.62 dolphin-2.5-mixtral-8x7b
- 5.62 OpenHermes-2.5-Mistral-7B
- 5.62 Nous-Hermes-2-Mixtral-8x7B-DPO
- 5.56 Samantha-1.11-70b
- 5.55 Orca-2-13b
- 5.54 blossom-v3_1-mistral-7b
- 5.54 Nous-Hermes-2-Llama-2-70B
- 5.53 Llama-2-70b-hf
- 5.50
Yi-34B
- 5.49 neural-chat-7b-v3-1
- 5.48 blossom-v4-mistral-7b
- 5.46 dolphin-2.7-mixtral-8x7b
- 5.45 orca_mini_v3_7b
- 5.43 deepseek-llm-7b-base
- 5.43 dolphin-2.6-mistral-7b-dpo
- 5.41 Mistral-7B-OpenOrca
- 5.40 dolphin-2.6-mistral-7b
- 5.40
Tulu 2 DPO 70B
- 5.39 dolphin-2.6-mistral-7b-dpo-las[..]
- 5.38 Llama-2-13b-hf
- 5.32 deepseek-llm-7b-chat
- 5.32
Qwen1.5-14B-Chat
- 5.25 Orca-2-7b
- 5.25 vicuna-13b-v1.5
- 5.23 mistral-7b-sft-alpha
- 5.19
Starling-LM-7B-alpha
- 5.16
Mixtral 8x7B
- 5.15 OpenHermes-Mixtral-8x7B
- 5.14 Mistral-7B-AEZAKMI-v1
- 5.07
Qwen1.5-7B
- 5.06 samantha-mistral-instruct-7b
- 5.06
Gemma 2B
- 5.05 Nous-Capybara-7B-V1.9
- 5.04 OpenHermes-7B
- 5.03 tulu-2-7b
- 5.03
Qwen1.5-4B-Chat
- 5.00 Nous-Capybara-7B-V1
- 5.00 OpenHermes-2-Mistral-7B
- 4.99 WizardLM-70B-V1.0
- 4.98
Qwen1.5-14B
- 4.95 miqu-1-70b-sf
- 4.90
Mistral-7B-Instruct-v0.1
- 4.77 neural-chat-7b-v3-3
- 4.74 WizardLM-13B-V1.2
- 4.66
Zephyr 7B Alpha
- 4.65 Toppy-M-7B
- 4.64 mythalion-13b
- 4.64 Xwin-LM-70B-V0.1
- 4.62 Llama-2-70b-chat-hf
- 4.57 Nous-Hermes-Llama2-13b
- 4.54 neural-chat-7b-v3-3-Slerp
- 4.53 Platypus2-70B-instruct
- 4.48 ReMM-v2.2-L2-13B
- 4.47 Llama-2-7B-32K-Instruct
- 4.46 mixtral-megamerge-dare-8x7b-v2
- 4.44 Llama-2-13b-chat-hf
- 4.44 ReMM-SLERP-L2-13B
- 4.43 firefly-mixtral-8x7b
- 4.43 MythoMax-L2-13b
- 4.40 mistral-7b-sft-beta
- 4.40 tulu-2-dpo-13b
- 4.37
Qwen1.5-7B-Chat
- 4.36 NeuralMonarch-7B
- 4.33 Llama-2-7b-chat-hf
- 4.33 Nous-Hermes-llama-2-7b
- 4.31 gemma-2b-it
- 4.30 samantha-1.2-mistral-7b
- 4.25 pygmalion-2-7b
- 4.24 AlphaMonarch-7B
- 4.24 yi-34B-v4
- 4.24
Zephyr 7B Beta
- 4.21 pygmalion-2-13b
- 4.04 Qwen1.5-1.8B-Chat
- 4.02 Qwen1.5-1.8B
- 3.95 Qwen1.5-0.5B-Chat
- 3.94 Mixtral-8x7B-Instruct-v0.1
- 3.78 tulu-2-dpo-7b
- 3.76
Mistral-7B-Instruct-v0.2
- 3.75 notus-7b-v1
- 3.75 Xwin-LM-7B-V0.2
- 3.65 gemma-7b-it
- 3.60 Xwin-LM-13B-V0.2
- 3.59 Qwen1.5-4B
- 3.52 Qwen1.5-0.5B
- 3.11 Yi-34B-Chat
- 1 GPT-4 Turbo Nov 2023, scenario instruction 9.54%
- 2 GPT-4 Turbo (Jan 2024) scenario instruction 9.53%
- 3 Claude 3 Opus 8.51%
- 4 GPT-3.5 Turbo Nov 2023, scenario instruction 8.30%
- 5 GPT-3.5 Turbo Jan 2024, scenario instruction 7.90%
- 6 claude-instant-v1.2 7.88%
- 7
Qwen1.5-72B 7.02%
- 8 Claude 2.1 6.87%
- 9 Yi-34B-200K-AEZAKMI-v2 6.86%
- 10 GPT-3.5 Turbo Jun 2023 6.80%
- 11 Claude 2 6.79%
- 12 tulu-2-70b 6.76%
- 13 dolphin-2.2-70b 6.64%
- 14
Gemini 1.0 Pro 6.51%
- 15 Mixtral-SlimOrca-8x7B 6.50%
- 16 Instruct_Mixtral-8x7B-v0.1_Dol[..] 6.49%
- 17 Nous-Hermes-2-Yi-34B 6.40%
- 18
DeepSeek LLM 67B 6.39%
- 19 Claude 3 Sonnet scenario instruction 6.39%
- 20 dolphin-2.2-yi-34b-200k 6.38%
- 21 Yi-34B-AEZAKMI-v1 6.38%
- 22 yi-34B-v2 6.30%
- 23 Nous-Hermes-2-Mixtral-8x7B-SFT 6.25%
- 24 yi-34B-v3 6.24%
- 25 OrionStar-Yi-34B-Chat 6.15%
- 26 blossom-v4-yi-34b 6.13%
- 27 deepseek-llm-67b-base 6.12%
- 28 Llama-2-7b-hf 6.11%
- 29 Yi-34B-200K-DARE-merge-v5 6.08%
- 30 Capybara-Tess-Yi-34B-200K 6.06%
- 31 platypus-yi-34b 6.03%
- 32 openchat-3.5-0106 5.99%
- 33 notux-8x7b-v1 5.96%
- 34 orca_mini_v3_13b 5.96%
- 35 SOLAR-0-70b-16bit 5.94%
- 36 Mistral-7B-AEZAKMI-v2 5.92%
- 37 samantha-mistral-7b 5.87%
- 38
Gemma 7B 5.79%
- 39 GPT-3.5 Turbo (Mar 2023) 5.78%
- 40 vicuna-7b-v1.5 5.76%
- 41 openchat-3.5-1210 5.74%
- 42 dolphin-2.6-mixtral-8x7b 5.73%
- 43 neural-chat-7b-v3-2 5.73%
- 44 blossom-v3-mistral-7b 5.69%
- 45 tulu-2-13b 5.69%
- 46 dolphin-2.2.1-mistral-7b 5.66%
- 47 CaPlatTessDolXaBoros-Yi-34B-20[..] 5.64%
- 48 orca_mini_v3_70b 5.63%
- 49
Mistral 7B v0.1 5.63%
- 50 dolphin-2.5-mixtral-8x7b 5.62%
- 51 OpenHermes-2.5-Mistral-7B 5.62%
- 52 Nous-Hermes-2-Mixtral-8x7B-DPO 5.62%
- 53 Samantha-1.11-70b 5.56%
- 54 Orca-2-13b 5.55%
- 55 blossom-v3_1-mistral-7b 5.54%
- 56 Nous-Hermes-2-Llama-2-70B 5.54%
- 57 Llama-2-70b-hf 5.53%
- 58
Yi-34B 5.50%
- 59 neural-chat-7b-v3-1 5.49%
- 60 blossom-v4-mistral-7b 5.48%
- 61 dolphin-2.7-mixtral-8x7b 5.46%
- 62 orca_mini_v3_7b 5.45%
- 63 deepseek-llm-7b-base 5.43%
- 64 dolphin-2.6-mistral-7b-dpo 5.43%
- 65 Mistral-7B-OpenOrca 5.41%
- 66 dolphin-2.6-mistral-7b 5.40%
- 67
Tulu 2 DPO 70B 5.40%
- 68 dolphin-2.6-mistral-7b-dpo-las[..] 5.39%
- 69 Llama-2-13b-hf 5.38%
- 70 deepseek-llm-7b-chat 5.32%
- 71
Qwen1.5-14B-Chat 5.32%
- 72 Orca-2-7b 5.25%
- 73 vicuna-13b-v1.5 5.25%
- 74 mistral-7b-sft-alpha 5.23%
- 75
Starling-LM-7B-alpha 5.19%
- 76
Mixtral 8x7B 5.16%
- 77 OpenHermes-Mixtral-8x7B 5.15%
- 78 Mistral-7B-AEZAKMI-v1 5.14%
- 79
Qwen1.5-7B 5.07%
- 80 samantha-mistral-instruct-7b 5.06%
- 81
Gemma 2B 5.06%
- 82 Nous-Capybara-7B-V1.9 5.05%
- 83 OpenHermes-7B 5.04%
- 84 tulu-2-7b 5.03%
- 85
Qwen1.5-4B-Chat 5.03%
- 86 Nous-Capybara-7B-V1 5.00%
- 87 OpenHermes-2-Mistral-7B 5.00%
- 88 WizardLM-70B-V1.0 4.99%
- 89
Qwen1.5-14B 4.98%
- 90 miqu-1-70b-sf 4.95%
- 91
Mistral-7B-Instruct-v0.1 4.90%
- 92 neural-chat-7b-v3-3 4.77%
- 93 WizardLM-13B-V1.2 4.74%
- 94
Zephyr 7B Alpha 4.66%
- 95 Toppy-M-7B 4.65%
- 96 mythalion-13b 4.64%
- 97 Xwin-LM-70B-V0.1 4.64%
- 98 Llama-2-70b-chat-hf scenario instruction 4.62%
- 99 Nous-Hermes-Llama2-13b 4.57%
- 100 neural-chat-7b-v3-3-Slerp 4.54%
- 101 Platypus2-70B-instruct 4.53%
- 102 ReMM-v2.2-L2-13B 4.48%
- 103 Llama-2-7B-32K-Instruct 4.47%
- 104 mixtral-megamerge-dare-8x7b-v2 4.46%
- 105 Llama-2-13b-chat-hf scenario instruction 4.44%
- 106 ReMM-SLERP-L2-13B 4.44%
- 107 firefly-mixtral-8x7b 4.43%
- 108 MythoMax-L2-13b 4.43%
- 109 mistral-7b-sft-beta 4.40%
- 110 tulu-2-dpo-13b 4.40%
- 111
Qwen1.5-7B-Chat 4.37%
- 112 NeuralMonarch-7B 4.36%
- 113 Llama-2-7b-chat-hf 4.33%
- 114 Nous-Hermes-llama-2-7b 4.33%
- 115 gemma-2b-it 4.31%
- 116 samantha-1.2-mistral-7b 4.30%
- 117 pygmalion-2-7b 4.25%
- 118 AlphaMonarch-7B 4.24%
- 119 yi-34B-v4 4.24%
- 120
Zephyr 7B Beta 4.24%
- 121 pygmalion-2-13b 4.21%
- 122 Qwen1.5-1.8B-Chat 4.04%
- 123 Qwen1.5-1.8B 4.02%
- 124 Qwen1.5-0.5B-Chat 3.95%
- 125 Mixtral-8x7B-Instruct-v0.1 3.94%
- 126 tulu-2-dpo-7b 3.78%
- 127
Mistral-7B-Instruct-v0.2 3.76%
- 128 notus-7b-v1 3.75%
- 129 Xwin-LM-7B-V0.2 3.75%
- 130 gemma-7b-it 3.65%
- 131 Xwin-LM-13B-V0.2 3.60%
- 132 Qwen1.5-4B 3.59%
- 133 Qwen1.5-0.5B 3.52%
- 134 Yi-34B-Chat 3.11%
Source: The RuLES 2.0 paper
- 9.54 GPT-4 Turbo
- 9.53 GPT-4 Turbo (Jan 2024)
- 8.51 Claude 3 Opus
- 8.30 GPT-3.5 Turbo
- 7.90 GPT-3.5 Turbo
- 7.02
Qwen1.5-72B
- 6.87 Claude 2.1
- 6.80 GPT-3.5 Turbo
- 6.79 Claude 2
- 6.51
Gemini 1.0 Pro
- 6.39
DeepSeek LLM 67B
- 6.39 Claude 3 Sonnet
- 5.79
Gemma 7B
- 5.78 GPT-3.5 Turbo (Mar 2023)
- 5.63
Mistral 7B v0.1
- 5.62 Nous-Hermes-2-Mixtral-8x7B-DPO
- 5.50
Yi-34B
- 5.40
Tulu 2 DPO 70B
- 5.32
Qwen1.5-14B-Chat
- 5.19
Starling-LM-7B-alpha
- 5.16
Mixtral 8x7B
- 5.07
Qwen1.5-7B
- 5.06
Gemma 2B
- 5.03
Qwen1.5-4B-Chat
- 4.98
Qwen1.5-14B
- 4.90
Mistral-7B-Instruct-v0.1
- 4.66
Zephyr 7B Alpha
- 4.37
Qwen1.5-7B-Chat
- 4.24
Zephyr 7B Beta
- 3.76
Mistral-7B-Instruct-v0.2
- 1 GPT-4 Turbo Nov 2023, scenario instruction 9.54%
- 2 GPT-4 Turbo (Jan 2024) scenario instruction 9.53%
- 3 Claude 3 Opus 8.51%
- 4 GPT-3.5 Turbo Nov 2023, scenario instruction 8.30%
- 5 GPT-3.5 Turbo Jan 2024, scenario instruction 7.90%
- 6
Qwen1.5-72B 7.02%
- 7 Claude 2.1 6.87%
- 8 GPT-3.5 Turbo Jun 2023 6.80%
- 9 Claude 2 6.79%
- 10
Gemini 1.0 Pro 6.51%
- 11
DeepSeek LLM 67B 6.39%
- 12 Claude 3 Sonnet scenario instruction 6.39%
- 13
Gemma 7B 5.79%
- 14 GPT-3.5 Turbo (Mar 2023) 5.78%
- 15
Mistral 7B v0.1 5.63%
- 16 Nous-Hermes-2-Mixtral-8x7B-DPO 5.62%
- 17
Yi-34B 5.50%
- 18
Tulu 2 DPO 70B 5.40%
- 19
Qwen1.5-14B-Chat 5.32%
- 20
Starling-LM-7B-alpha 5.19%
- 21
Mixtral 8x7B 5.16%
- 22
Qwen1.5-7B 5.07%
- 23
Gemma 2B 5.06%
- 24
Qwen1.5-4B-Chat 5.03%
- 25
Qwen1.5-14B 4.98%
- 26
Mistral-7B-Instruct-v0.1 4.90%
- 27
Zephyr 7B Alpha 4.66%
- 28
Qwen1.5-7B-Chat 4.37%
- 29
Zephyr 7B Beta 4.24%
- 30
Mistral-7B-Instruct-v0.2 3.76%
Source: The RuLES 2.0 paper
| # | Entry | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | GPT-4 Turbo Nov 2023 | 9.54% | scenario instruction | Nov 2023 | Official leaderboard |
| 2 | GPT-4 Turbo (Jan 2024) | 9.53% | scenario instruction | Jan 2024 | Official leaderboard |
| 3 | Claude 3 Opus | 8.51% | Feb 2024 | Official leaderboard | |
| 4 | GPT-3.5 Turbo Nov 2023 | 8.30% | scenario instruction | Nov 2023 | Official leaderboard |
| 5 | GPT-3.5 Turbo Jan 2024 | 7.90% | scenario instruction | Jan 2024 | Official leaderboard |
| 6 | claude-instant-v1.2 | 7.88% | Official leaderboard | ||
| 7 | | 7.02% | Feb 2024 | Official leaderboard | |
| 8 | Claude 2.1 | 6.87% | Nov 2023 | Official leaderboard | |
| 9 | Yi-34B-200K-AEZAKMI-v2 | 6.86% | Official leaderboard | ||
| 10 | GPT-3.5 Turbo Jun 2023 | 6.80% | Jun 2023 | Official leaderboard | |
| 11 | Claude 2 | 6.79% | Jul 2023 | Official leaderboard | |
| 12 | tulu-2-70b | 6.76% | Official leaderboard | ||
| 13 | dolphin-2.2-70b | 6.64% | Official leaderboard | ||
| 14 | | 6.51% | Dec 2023 | Official leaderboard | |
| 15 | Mixtral-SlimOrca-8x7B | 6.50% | Official leaderboard | ||
| 16 | Instruct_Mixtral-8x7B-v0.1_Dol[..] | 6.49% | Official leaderboard | ||
| 17 | Nous-Hermes-2-Yi-34B | 6.40% | Official leaderboard | ||
| 18 | | 6.39% | Nov 2023 | Official leaderboard | |
| 19 | Claude 3 Sonnet | 6.39% | scenario instruction | Feb 2024 | Official leaderboard |
| 20 | dolphin-2.2-yi-34b-200k | 6.38% | Official leaderboard | ||
| 21 | Yi-34B-AEZAKMI-v1 | 6.38% | Official leaderboard | ||
| 22 | yi-34B-v2 | 6.30% | Official leaderboard | ||
| 23 | Nous-Hermes-2-Mixtral-8x7B-SFT | 6.25% | Official leaderboard | ||
| 24 | yi-34B-v3 | 6.24% | Official leaderboard | ||
| 25 | OrionStar-Yi-34B-Chat | 6.15% | Official leaderboard | ||
| 26 | blossom-v4-yi-34b | 6.13% | Official leaderboard | ||
| 27 | deepseek-llm-67b-base | 6.12% | Official leaderboard | ||
| 28 | Llama-2-7b-hf | 6.11% | Official leaderboard | ||
| 29 | Yi-34B-200K-DARE-merge-v5 | 6.08% | Official leaderboard | ||
| 30 | Capybara-Tess-Yi-34B-200K | 6.06% | Official leaderboard | ||
| 31 | platypus-yi-34b | 6.03% | Official leaderboard | ||
| 32 | openchat-3.5-0106 | 5.99% | Official leaderboard | ||
| 33 | notux-8x7b-v1 | 5.96% | Official leaderboard | ||
| 34 | orca_mini_v3_13b | 5.96% | Official leaderboard | ||
| 35 | SOLAR-0-70b-16bit | 5.94% | Official leaderboard | ||
| 36 | Mistral-7B-AEZAKMI-v2 | 5.92% | Official leaderboard | ||
| 37 | samantha-mistral-7b | 5.87% | Official leaderboard | ||
| 38 | | 5.79% | Feb 2024 | Official leaderboard | |
| 39 | GPT-3.5 Turbo (Mar 2023) | 5.78% | Mar 2023 | Official leaderboard | |
| 40 | vicuna-7b-v1.5 | 5.76% | Official leaderboard | ||
| 41 | openchat-3.5-1210 | 5.74% | Official leaderboard | ||
| 42 | dolphin-2.6-mixtral-8x7b | 5.73% | Official leaderboard | ||
| 43 | neural-chat-7b-v3-2 | 5.73% | Official leaderboard | ||
| 44 | blossom-v3-mistral-7b | 5.69% | Official leaderboard | ||
| 45 | tulu-2-13b | 5.69% | Official leaderboard | ||
| 46 | dolphin-2.2.1-mistral-7b | 5.66% | Official leaderboard | ||
| 47 | CaPlatTessDolXaBoros-Yi-34B-20[..] | 5.64% | Official leaderboard | ||
| 48 | orca_mini_v3_70b | 5.63% | Official leaderboard | ||
| 49 | | 5.63% | Sep 2023 | Official leaderboard | |
| 50 | dolphin-2.5-mixtral-8x7b | 5.62% | Official leaderboard | ||
| 51 | OpenHermes-2.5-Mistral-7B | 5.62% | Official leaderboard | ||
| 52 | Nous-Hermes-2-Mixtral-8x7B-DPO | 5.62% | Jan 2024 | Official leaderboard | |
| 53 | Samantha-1.11-70b | 5.56% | Official leaderboard | ||
| 54 | Orca-2-13b | 5.55% | Official leaderboard | ||
| 55 | blossom-v3_1-mistral-7b | 5.54% | Official leaderboard | ||
| 56 | Nous-Hermes-2-Llama-2-70B | 5.54% | Official leaderboard | ||
| 57 | Llama-2-70b-hf | 5.53% | Official leaderboard | ||
| 58 | | 5.50% | Nov 2023 | Official leaderboard | |
| 59 | neural-chat-7b-v3-1 | 5.49% | Official leaderboard | ||
| 60 | blossom-v4-mistral-7b | 5.48% | Official leaderboard | ||
| 61 | dolphin-2.7-mixtral-8x7b | 5.46% | Official leaderboard | ||
| 62 | orca_mini_v3_7b | 5.45% | Official leaderboard | ||
| 63 | deepseek-llm-7b-base | 5.43% | Official leaderboard | ||
| 64 | dolphin-2.6-mistral-7b-dpo | 5.43% | Official leaderboard | ||
| 65 | Mistral-7B-OpenOrca | 5.41% | Official leaderboard | ||
| 66 | dolphin-2.6-mistral-7b | 5.40% | Official leaderboard | ||
| 67 | | 5.40% | Nov 2023 | Official leaderboard | |
| 68 | dolphin-2.6-mistral-7b-dpo-las[..] | 5.39% | Official leaderboard | ||
| 69 | Llama-2-13b-hf | 5.38% | Official leaderboard | ||
| 70 | deepseek-llm-7b-chat | 5.32% | Official leaderboard | ||
| 71 | | 5.32% | Feb 2024 | Official leaderboard | |
| 72 | Orca-2-7b | 5.25% | Official leaderboard | ||
| 73 | vicuna-13b-v1.5 | 5.25% | Official leaderboard | ||
| 74 | mistral-7b-sft-alpha | 5.23% | Official leaderboard | ||
| 75 | | 5.19% | Nov 2023 | Official leaderboard | |
| 76 | | 5.16% | Dec 2023 | Official leaderboard | |
| 77 | OpenHermes-Mixtral-8x7B | 5.15% | Official leaderboard | ||
| 78 | Mistral-7B-AEZAKMI-v1 | 5.14% | Official leaderboard | ||
| 79 | | 5.07% | Feb 2024 | Official leaderboard | |
| 80 | samantha-mistral-instruct-7b | 5.06% | Official leaderboard | ||
| 81 | | 5.06% | Feb 2024 | Official leaderboard | |
| 82 | Nous-Capybara-7B-V1.9 | 5.05% | Official leaderboard | ||
| 83 | OpenHermes-7B | 5.04% | Official leaderboard | ||
| 84 | tulu-2-7b | 5.03% | Official leaderboard | ||
| 85 | | 5.03% | Feb 2024 | Official leaderboard | |
| 86 | Nous-Capybara-7B-V1 | 5.00% | Official leaderboard | ||
| 87 | OpenHermes-2-Mistral-7B | 5.00% | Official leaderboard | ||
| 88 | WizardLM-70B-V1.0 | 4.99% | Official leaderboard | ||
| 89 | | 4.98% | Feb 2024 | Official leaderboard | |
| 90 | miqu-1-70b-sf | 4.95% | Official leaderboard | ||
| 91 | | 4.90% | Sep 2023 | Official leaderboard | |
| 92 | neural-chat-7b-v3-3 | 4.77% | Official leaderboard | ||
| 93 | WizardLM-13B-V1.2 | 4.74% | Official leaderboard | ||
| 94 | | 4.66% | Oct 2023 | Official leaderboard | |
| 95 | Toppy-M-7B | 4.65% | Official leaderboard | ||
| 96 | mythalion-13b | 4.64% | Official leaderboard | ||
| 97 | Xwin-LM-70B-V0.1 | 4.64% | Official leaderboard | ||
| 98 | Llama-2-70b-chat-hf | 4.62% | scenario instruction | Official leaderboard | |
| 99 | Nous-Hermes-Llama2-13b | 4.57% | Official leaderboard | ||
| 100 | neural-chat-7b-v3-3-Slerp | 4.54% | Official leaderboard | ||
| 101 | Platypus2-70B-instruct | 4.53% | Official leaderboard | ||
| 102 | ReMM-v2.2-L2-13B | 4.48% | Official leaderboard | ||
| 103 | Llama-2-7B-32K-Instruct | 4.47% | Official leaderboard | ||
| 104 | mixtral-megamerge-dare-8x7b-v2 | 4.46% | Official leaderboard | ||
| 105 | Llama-2-13b-chat-hf | 4.44% | scenario instruction | Official leaderboard | |
| 106 | ReMM-SLERP-L2-13B | 4.44% | Official leaderboard | ||
| 107 | firefly-mixtral-8x7b | 4.43% | Official leaderboard | ||
| 108 | MythoMax-L2-13b | 4.43% | Official leaderboard | ||
| 109 | mistral-7b-sft-beta | 4.40% | Official leaderboard | ||
| 110 | tulu-2-dpo-13b | 4.40% | Official leaderboard | ||
| 111 | | 4.37% | Feb 2024 | Official leaderboard | |
| 112 | NeuralMonarch-7B | 4.36% | Official leaderboard | ||
| 113 | Llama-2-7b-chat-hf | 4.33% | Official leaderboard | ||
| 114 | Nous-Hermes-llama-2-7b | 4.33% | Official leaderboard | ||
| 115 | gemma-2b-it | 4.31% | Official leaderboard | ||
| 116 | samantha-1.2-mistral-7b | 4.30% | Official leaderboard | ||
| 117 | pygmalion-2-7b | 4.25% | Official leaderboard | ||
| 118 | AlphaMonarch-7B | 4.24% | Official leaderboard | ||
| 119 | yi-34B-v4 | 4.24% | Official leaderboard | ||
| 120 | | 4.24% | Oct 2023 | Official leaderboard | |
| 121 | pygmalion-2-13b | 4.21% | Official leaderboard | ||
| 122 | Qwen1.5-1.8B-Chat | 4.04% | Official leaderboard | ||
| 123 | Qwen1.5-1.8B | 4.02% | Official leaderboard | ||
| 124 | Qwen1.5-0.5B-Chat | 3.95% | Official leaderboard | ||
| 125 | Mixtral-8x7B-Instruct-v0.1 | 3.94% | Official leaderboard | ||
| 126 | tulu-2-dpo-7b | 3.78% | Official leaderboard | ||
| 127 | | 3.76% | Dec 2023 | Official leaderboard | |
| 128 | notus-7b-v1 | 3.75% | Official leaderboard | ||
| 129 | Xwin-LM-7B-V0.2 | 3.75% | Official leaderboard | ||
| 130 | gemma-7b-it | 3.65% | Official leaderboard | ||
| 131 | Xwin-LM-13B-V0.2 | 3.60% | Official leaderboard | ||
| 132 | Qwen1.5-4B | 3.59% | Official leaderboard | ||
| 133 | Qwen1.5-0.5B | 3.52% | Official leaderboard | ||
| 134 | Yi-34B-Chat | 3.11% | Official leaderboard |
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | GPT-4 Turbo Nov 2023 | 9.54% | scenario instruction | Nov 2023 | Official leaderboard |
| 2 | GPT-4 Turbo (Jan 2024) | 9.53% | scenario instruction | Jan 2024 | Official leaderboard |
| 3 | Claude 3 Opus | 8.51% | Feb 2024 | Official leaderboard | |
| 4 | GPT-3.5 Turbo Nov 2023 | 8.30% | scenario instruction | Nov 2023 | Official leaderboard |
| 5 | GPT-3.5 Turbo Jan 2024 | 7.90% | scenario instruction | Jan 2024 | Official leaderboard |
| 6 | | 7.02% | Feb 2024 | Official leaderboard | |
| 7 | Claude 2.1 | 6.87% | Nov 2023 | Official leaderboard | |
| 8 | GPT-3.5 Turbo Jun 2023 | 6.80% | Jun 2023 | Official leaderboard | |
| 9 | Claude 2 | 6.79% | Jul 2023 | Official leaderboard | |
| 10 | | 6.51% | Dec 2023 | Official leaderboard | |
| 11 | | 6.39% | Nov 2023 | Official leaderboard | |
| 12 | Claude 3 Sonnet | 6.39% | scenario instruction | Feb 2024 | Official leaderboard |
| 13 | | 5.79% | Feb 2024 | Official leaderboard | |
| 14 | GPT-3.5 Turbo (Mar 2023) | 5.78% | Mar 2023 | Official leaderboard | |
| 15 | | 5.63% | Sep 2023 | Official leaderboard | |
| 16 | Nous-Hermes-2-Mixtral-8x7B-DPO | 5.62% | Jan 2024 | Official leaderboard | |
| 17 | | 5.50% | Nov 2023 | Official leaderboard | |
| 18 | | 5.40% | Nov 2023 | Official leaderboard | |
| 19 | | 5.32% | Feb 2024 | Official leaderboard | |
| 20 | | 5.19% | Nov 2023 | Official leaderboard | |
| 21 | | 5.16% | Dec 2023 | Official leaderboard | |
| 22 | | 5.07% | Feb 2024 | Official leaderboard | |
| 23 | | 5.06% | Feb 2024 | Official leaderboard | |
| 24 | | 5.03% | Feb 2024 | Official leaderboard | |
| 25 | | 4.98% | Feb 2024 | Official leaderboard | |
| 26 | | 4.90% | Sep 2023 | Official leaderboard | |
| 27 | | 4.66% | Oct 2023 | Official leaderboard | |
| 28 | | 4.37% | Feb 2024 | Official leaderboard | |
| 29 | | 4.24% | Oct 2023 | Official leaderboard | |
| 30 | | 3.76% | Dec 2023 | Official leaderboard |
Rankings by part
We read 6 parts from the benchmark’s paper, each ranking models on one part of the test, such as Benign harmless, Benign helpful and Basic harmless. GPT-4 Turbo leads 3 of them, and 2 other models lead the rest. Arrows show how far a model moved from its overall rank among the models we track.
Benign harmless
30 models we track have a score here.
- 1
Mistral-7B-Instruct-v0.1 ↑25 10%
- 2
Mistral 7B v0.1 ↑13 10%
- 3
Yi-34B ↑14 10%
- 4 GPT-4 Turbo Nov 2023 ↓3 10%
- 5 GPT-4 Turbo (Jan 2024) ↓3 10%
- 6
Gemma 7B ↑7 10%
- 7
Zephyr 7B Alpha ↑20 9.96%
- 8
Zephyr 7B Beta ↑21 9.96%
- 9
Mixtral 8x7B ↑12 9.96%
- 10
Qwen1.5-7B ↑12 9.96%
Benign helpful
30 models we track have a score here.
- 1 GPT-4 Turbo Nov 2023 10%
- 2 GPT-4 Turbo (Jan 2024) 10%
- 3 Claude 3 Opus 9.80%
- 4 Claude 2 ↑5 9.56%
- 5 Claude 2.1 ↑2 9.56%
- 6 GPT-3.5 Turbo Jan 2024 ↓1 9.56%
- 7
Qwen1.5-72B ↓1 9.56%
- 8
Gemini 1.0 Pro ↑2 9.16%
- 9 Claude 3 Sonnet ↑3 9.12%
- 10 GPT-3.5 Turbo Nov 2023 ↓6 8.44%
Basic harmless
30 models we track have a score here.
- 1 GPT-4 Turbo (Jan 2024) ↑1 9.96%
- 2 GPT-4 Turbo Nov 2023 ↓1 9.91%
- 3 GPT-3.5 Turbo Nov 2023 ↑1 9.47%
- 4 Claude 3 Opus ↓1 8.98%
- 5 GPT-3.5 Turbo Jun 2023 ↑3 8.80%
- 6 GPT-3.5 Turbo Jan 2024 ↓1 8.67%
- 7
Gemma 2B ↑16 7.16%
- 8
Gemini 1.0 Pro ↑2 7.07%
- 9 GPT-3.5 Turbo (Mar 2023) ↑5 6.80%
- 10
DeepSeek LLM 67B ↑1 6.80%
Basic helpful
30 models we track have a score here.
- 1 GPT-4 Turbo Nov 2023 9.36%
- 2 GPT-4 Turbo (Jan 2024) 9.20%
- 3 Claude 3 Opus 7.28%
- 4 GPT-3.5 Turbo Nov 2023 6.32%
- 5 GPT-3.5 Turbo Jan 2024 6.28%
- 6
Qwen1.5-72B 5.88%
- 7 Claude 3 Sonnet ↑5 5.48%
- 8
DeepSeek LLM 67B ↑3 5.20%
- 9 Claude 2.1 ↓2 5.04%
- 10 Claude 2 ↓1 4.84%
Redteam harmless
30 models we track have a score here.
- 1 GPT-4 Turbo (Jan 2024) ↑1 9.13%
- 2 GPT-4 Turbo Nov 2023 ↓1 9.10%
- 3 Claude 3 Opus 8.82%
- 4 GPT-3.5 Turbo Nov 2023 7.94%
- 5
Gemma 2B ↑18 7.94%
- 6 GPT-3.5 Turbo Jan 2024 ↓1 7.30%
- 7 Claude 2.1 7.18%
- 8 GPT-3.5 Turbo Jun 2023 6.76%
- 9
Mistral 7B v0.1 ↑6 6.65%
- 10 Claude 2 ↓1 6.59%
Redteam helpful
30 models we track have a score here.
- 1 GPT-4 Turbo Nov 2023 8.90%
- 2 GPT-4 Turbo (Jan 2024) 8.90%
- 3 GPT-3.5 Turbo Nov 2023 ↑1 7.92%
- 4 GPT-3.5 Turbo Jan 2024 ↑1 7.10%
- 5 Claude 3 Opus ↓2 6.49%
- 6 Claude 2.1 ↑1 5.59%
- 7
Qwen1.5-72B ↓1 5.21%
- 8 Claude 2 ↑1 5.10%
- 9
DeepSeek LLM 67B ↑2 5.00%
- 10 Claude 3 Sonnet ↑2 4.85%
Scores at each effort level
Models the leaderboard ran at two or more effort levels. We don’t have enough cost data here to say what the extra effort costs.
Source: The RuLES 2.0 paper
Scores at each effort level
Models the leaderboard ran at two or more effort levels. We don’t have enough cost data here to say what the extra effort costs.
Source: The RuLES 2.0 paper
Number one over time
Lab claims count from the day the card came out, independent runs from the model’s release.
Source: The RuLES 2.0 paper
Scores over time
All the scores we have, one dot each, so a model tested at several settings appears more than once.
Source: Official RuLES 2.0 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.
Versions
We switch the top row to each new version when it comes out. Open it for one row per version. An old version stays in play while people still test it, so whoever first takes it past 85% gets credit for closing it out.
Source: Official leaderboards
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
9 of 10 checks pass, 1 warning. Look first at the Newest score check. The newest came 2 years ago, in February 2024, for Claude 3 Opus. Every benchmark
Catalog record 2 pass
- Pass Task access All tasks are public.
- Pass Confidence Checked against a primary source.
Scores 1 warning 3 pass 1 note
- Pass Independent runs Scores from the benchmark’s paper (134 entries).
- Pass Models scored 30 models we track, plus 104 other entries on its leaderboard.
- Warning Newest score The newest came 2 years ago, in February 2024, for Claude 3 Opus.
- Note Frontier models None of the top 10 has a score. The strongest tested is Claude 3 Opus (#173).
- Pass Headroom The best is 9.54%, under 85%, so it still separates models.
Leaderboard import 3 pass
- Pass Importer We read the board on arxiv.org: 38 rows for models we track and 104 other entries at the last read.
- 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.