The LLM benchmark aggregator.

Qwen 2.5 Instruct Turbo (72B)

Alibaba · 72B

Strongest in Safe-prompt compliance (#13 of 82), weakest in Secure code (#141 of 274). Above par in 8 of 10 scopes. Among the models it meets almost everywhere, it finishes behind Claude Opus 4.8 and Grok 4.7 and ahead of GLM-5.3 Flash and Qwen3.8 Max.

§ 1 · Profile

What it is good at

Bars run from 50 — the average of the models each source lists — so right of the line is above par. The middle column is the gap to whoever leads that scope.

Safety56.5−5#34/3372/3

Safe-prompt compliance58.4−2#13/821/1

Fairness65.4−4.6#22/3002/2

Toxicity avoidance55.8−3.2#88/2721/1

Harm refusal53.9−7.7#91/3002/2

Jailbreak resistance56.4−8.5#95/2721/1

Secure code51.7−14.8#141/2741/1

Professional49.3−12.3#89/1681/1

Legal50.9−16.2#72/1511/1

Medical46.7−20.1#98/1401/1

§ 2 · Head to head

What it beats, and what beats it

The same models turn up scope after scope. Counted once: where both were placed, who finished higher. Bars run right for Qwen 2.5 Instruct Turbo (72B), left for the other.

OLMo 7B Instruct Hfwon 6 · lost 0

RakutenAI 7B Chatwon 6 · lost 0

SmolLM 1.7B Instructwon 6 · lost 0

PowerMoE 3Bwon 6 · lost 0

Phi 2won 6 · lost 0

Qwen2.5 7B Instructwon 6 · lost 0

Gemma 7B Itwon 6 · lost 0

H2o Danube3 500M Chatwon 6 · lost 0

PowerLM 3Bwon 6 · lost 0

Smollm2 1.7B Instructwon 6 · lost 0

LFM2 350Mwon 6 · lost 0

Laguna Xs 2.1won 6 · lost 0

RakutenAI 7B Instructwon 6 · lost 0

Falcon Mamba 7B Instructwon 6 · lost 0

Nous Hermes 2 Mixtral 8x7b Dpowon 6 · lost 0

SmolLM2 360M Instructwon 6 · lost 0

Qwen2.5 0.5B Instructwon 6 · lost 0

Jamba Mini 1.7won 6 · lost 0

Magistral Smallwon 6 · lost 0

Falcon H1 0.5B Instructwon 6 · lost 0

SEA LION V1 7B ITwon 6 · lost 0

Llama 3.1 8B Instructwon 6 · lost 0

Qwen1.5 14B Chatwon 6 · lost 0

Zephyr 7B Betawon 6 · lost 0

Magistral Mediumwon 6 · lost 0

LFM2 700Mwon 6 · lost 0

Jamba Large 1.7won 6 · lost 0

NexusRaven V2 13Bwon 6 · lost 0

Open Mixtral 8x7bwon 6 · lost 0

Qwen2.5 3B Instructwon 6 · lost 0

LFM2 1.2Bwon 6 · lost 0

Aya 23 35Bwon 6 · lost 0

Granite 3.0 1B A400M Instructwon 6 · lost 0

QwQ 32Bwon 6 · lost 0

Jamba Instructwon 6 · lost 0

SeaLLMs V3 7B Chatwon 6 · lost 0

DeepSeek Reasonerwon 6 · lost 0

Mistral Small 24B Instructwon 6 · lost 0

Hunyuan A13B Instructwon 6 · lost 0

Gemma 3 4B Itwon 6 · lost 0

Open Mixtral 8x22bwon 6 · lost 0

Gemma2 9B Cpt Sea Lionv3 Instructwon 6 · lost 0

LongWriter Glm4 9Bwon 6 · lost 0

Qwen2.5 14B Instructwon 6 · lost 0

Command Rwon 6 · lost 0

OLMoE 1B-7B Instructwon 7 · lost 0

Mistral Instruct v0.1 (7B)won 7 · lost 0

DBRX Instructwon 7 · lost 0

GPT-3.5 Turbowon 7 · lost 0

Gemini 2.0 Flash Litewon 7 · lost 0

Mixtral (8x7B)won 7 · lost 0

Mistral Smallwon 8 · lost 0

Jamba 1.6 Miniwon 9 · lost 0

Jamba 1.6 Largewon 9 · lost 0

Jamba 1.5 Largewon 9 · lost 0

Qwen 2.5 Instruct Turbo (7B)won 9 · lost 0

Gemini 1.5 Prowon 10 · lost 0

GPT-4.1 Nanowon 9 · lost 1

Llama 4 Maverick Instructwon 9 · lost 1

Command R Pluswon 9 · lost 1

DeepSeek V3won 9 · lost 1

Gemini 1.5 Flashwon 8 · lost 1

Jamba 1.5 Miniwon 8 · lost 1

Llama 3.1 Instruct Turbo (8B)won 8 · lost 1

Llama 3.1 Instruct Turbo (70B)won 8 · lost 1

Gemma 2 9B Itwon 7 · lost 1

Llama 3.3 Instruct Turbo (70B)won 7 · lost 1

Mistral Largewon 7 · lost 1

Gemma 4 31Bwon 7 · lost 1

Mistral Instruct v0.3 (7B)won 6 · lost 1

OLMo 2 7B Instructwon 6 · lost 1

DeepSeek LLM 67B Chatwon 6 · lost 1

Llama 3 8B Instructwon 6 · lost 1

Gemini 2.5 Flash Litewon 6 · lost 1

Qwen3 30B A3B Instructwon 5 · lost 1

GLM-4 9B Chatwon 5 · lost 1

CodeLlama 7B Instruct Hfwon 5 · lost 1

Qwen2 7B Instructwon 5 · lost 1

Gemma 2B Itwon 5 · lost 1

Aya 23 8Bwon 5 · lost 1

Laguna S 2.1won 5 · lost 1

Grok Build 0.1won 5 · lost 1

DeepSeek R1 Distill Qwen 7Bwon 5 · lost 1

DeepSeek R1 Distill Llama 8Bwon 5 · lost 1

H2o Danube3 4B Chatwon 5 · lost 1

Ling 3.0 Flash VLwon 5 · lost 1

Command R7Bwon 5 · lost 1

SmolLM 360M Instructwon 5 · lost 1

Granite 3.2 8B Instructwon 5 · lost 1

Mistral 7B Instruct V0.2won 5 · lost 1

Nemotron 3 Ultra 550B A55Bwon 5 · lost 1

Phi-4 Mini Instructwon 5 · lost 1

Open Codestral Mambawon 5 · lost 1

Mimo V2.6 Pro Ultraspeedwon 5 · lost 1

DeepSeek V3p1won 5 · lost 1

Gemma 4 E2Bwon 5 · lost 1

Yi 1.5 9B Chatwon 5 · lost 1

Sarvam 1won 5 · lost 1

Qwen2.5 7B Instruct 1Mwon 5 · lost 1

Qwen2.5 1.5B Instructwon 5 · lost 1

Granite 3.1 2B Instructwon 5 · lost 1

WizardLM 2.8x22Bwon 5 · lost 1

Llama 3.2 3B Instructwon 5 · lost 1

Gemma 2 2B Itwon 5 · lost 1

Kimi K2.7 Codewon 5 · lost 1

Gemma 4 12Bwon 5 · lost 1

Granite 3.2 2B Instructwon 5 · lost 1

Fuguwon 5 · lost 1

Granite 3.0 3B A800M Instructwon 5 · lost 1

Starling Lm 7B Betawon 5 · lost 1

Granite 3.0 2B Instructwon 5 · lost 1

Reflection Llama 3.1 70Bwon 5 · lost 1

Gemma 4 26B A4Bwon 5 · lost 1

DeepSeek Chatwon 5 · lost 1

Qwen2.5 32B Instructwon 5 · lost 1

Qwen2.5 14B Instruct 1Mwon 5 · lost 1

Qwen2 VL 72Bwon 5 · lost 1

GLM-5 Turbowon 5 · lost 1

Qwen3 Vl 235B A22B Instructwon 5 · lost 1

Phi 3 Medium 128k Instructwon 5 · lost 1

Gemma 3 27B Itwon 5 · lost 1

GPT-5.6 Astrawon 5 · lost 1

Phi 3 Small 128k Instructwon 5 · lost 1

GPT OSS Safeguard 20Bwon 5 · lost 1

EAI Llama 3.1 8B Instruct SageAlignwon 5 · lost 1

Gemma 3 12B Itwon 5 · lost 1

Apertus 70B Instructwon 5 · lost 1

Nova Prowon 5 · lost 1

EAI SageAlign 8B LoRAwon 5 · lost 1

Qwen3.5 27Bwon 5 · lost 1

Qwen3.5 122B A10Bwon 5 · lost 1

Fugu Ultra V2won 5 · lost 1

Llama 4 Scout Instructwon 8 · lost 2

Gemini 2.0 Flashwon 8 · lost 2

Ling 3.0 Flashwon 7 · lost 2

Command Awon 7 · lost 2

Mimo V2.5 Prowon 7 · lost 2

DeepSeek V3.2won 7 · lost 2

Llama 3.1 Instruct Turbo (405B)won 7 · lost 2

GLM-5.1won 7 · lost 2

Grok 4.1 Fastwon 7 · lost 2

GLM-4.5won 7 · lost 2

Mimo V2.6 Flashwon 6 · lost 2

IBM Granite 4.0 Microwon 5 · lost 2

Llama 3 70B Instructwon 5 · lost 2

Gemini 3 Prowon 5 · lost 2

GPT OSS 20Bwon 7 · lost 3

GPT OSS 120Bwon 7 · lost 3

DeepSeek R1won 7 · lost 3

Grok 4won 7 · lost 3

GPT-4.1 Miniwon 7 · lost 3

Qwen3 8Bwon 4 · lost 2

NVIDIA Nemotron 3 Super 120B A12Bwon 4 · lost 2

Gemma 4 E4Bwon 4 · lost 2

Komodo 7B Basewon 4 · lost 2

Dolphin 2.5 Mixtral 8x7bwon 4 · lost 2

Apertus 8B Instructwon 4 · lost 2

Granite 3.1 3B A800M Instructwon 4 · lost 2

Phi 3 Medium 4k Instructwon 4 · lost 2

Granite 3.1 8B Instructwon 4 · lost 2

Sarvam 30Bwon 4 · lost 2

Qwen2 57B A14B Instructwon 4 · lost 2

Smaug Llama 3 70B Instructwon 4 · lost 2

Granite 3.0 8B Instructwon 4 · lost 2

Granite 4.0 H Microwon 4 · lost 2

Granite 4.0 H Tinywon 4 · lost 2

Phi 3 Small 8k Instructwon 4 · lost 2

Phi 3 Mini 128k Instructwon 4 · lost 2

Phi 3.5 Mini Instructwon 4 · lost 2

K2 Chatwon 4 · lost 2

Phi 3 Mini 4k Instructwon 4 · lost 2

Krutrim 2 Instructwon 4 · lost 2

Qwen3.5 35B A3Bwon 4 · lost 2

Phi 3.5 MoE Instructwon 4 · lost 2

Nova Litewon 4 · lost 2

Nova Premierwon 4 · lost 2

GPT-4o Miniwon 6 · lost 3

Grok 4.3won 6 · lost 3

Kimi K2.5won 6 · lost 3

GPT-6 Lunawon 6 · lost 3

DeepSeek V4 Flashwon 6 · lost 3

Qwen3.7 Maxwon 6 · lost 3

Kimi K2.6won 6 · lost 3

GPT-6 Solwon 6 · lost 3

Grok 3won 6 · lost 3

DeepSeek V4 Prowon 6 · lost 3

Gemini 3.5 Flashwon 6 · lost 3

GPT-5 Nanowon 6 · lost 4

Claude Haiku 4.5won 6 · lost 4

O3 Miniwon 6 · lost 4

O4 Miniwon 6 · lost 4

Gemini 2.5 Prowon 6 · lost 4

GLM-4.6won 5 · lost 4

GLM-5.2won 5 · lost 4

Gemini 3.6 Flashwon 5 · lost 4

Gemini 3.8 Flashwon 5 · lost 4

Kimi K2 Thinkingwon 5 · lost 4

Grok 4.5won 5 · lost 4

MiniMax M3won 5 · lost 4

Qwen3.8 Maxwon 5 · lost 4

GLM-5.3 Flashwon 5 · lost 4

Llama 3.2 1B Instructwon 3 · lost 3

Llama 3 70B Chat HFwon 3 · lost 3

SeaLLM 7B V2won 3 · lost 3

Llama 3.1 Tulu 3 8B SFTwon 3 · lost 3

Llama 3.1 Tulu 3 8B DPOwon 3 · lost 3

Llama 3.1 Tulu 3 8Bwon 3 · lost 3

Qwen Maxwon 3 · lost 3

GPT-4won 3 · lost 3

Nova Microwon 3 · lost 3

Llama 3 8B Chat Hfwon 3 · lost 3

Llama 3.1 Nemotron 70B Instruct HFwon 3 · lost 3

Internlm2 Chat 20Bwon 3 · lost 3

Qwen2.5 72B Instructwon 3 · lost 3

Llama 3 8B Instruct RRwon 3 · lost 3

Granite 4.0 H Smallwon 3 · lost 3

Llama 3 8B Instruct MopeyMulewon 3 · lost 3

Cogito 671B V2 P1won 3 · lost 3

Qwen3.5 397B A17Bwon 3 · lost 3

Gemma 2 27B Itwon 4 · lost 4

Mimo V2.6 Prowon 4 · lost 4

Kimi K2won 5 · lost 5

Gemini 2.5 Flashwon 5 · lost 5

GPT-5.6 Lunawon 4 · lost 5

GPT-5.6 Terrawon 4 · lost 5

GPT-5.6 Solwon 4 · lost 5

GPT-5.5won 4 · lost 5

Claude 3 Haikuwon 3 · lost 4

Qwen2 72B Instructwon 3 · lost 4

Claude 3 Sonnetwon 3 · lost 4

Llama 3.2 Vision (11B)won 3 · lost 4

Claude Sonnet 4.6won 3 · lost 4

Claude Opus 4.6won 3 · lost 4

Claude Sonnet 4won 4 · lost 6

Qwen3 235B A22B Instructwon 4 · lost 6

Claude 3.7 Sonnetwon 4 · lost 6

Claude 3.5 Haikuwon 3 · lost 5

C4ai Aya Expanse 32Bwon 2 · lost 4

C4ai Aya Expanse 8Bwon 2 · lost 4

Titan Text Express V1won 2 · lost 4

Llama 2 70B Chat Hfwon 2 · lost 4

Llama 2 13B Chat Hfwon 2 · lost 4

Llama 2 7B Chat Hfwon 2 · lost 4

Sarvam 105Bwon 2 · lost 4

Llama 3.2 90B Vision Instruct Turbowon 2 · lost 4

Hy3won 2 · lost 4

MiniMax M2.7won 3 · lost 6

Claude 3.5 Sonnetwon 3 · lost 6

O1 Miniwon 3 · lost 6

GPT-5.4won 3 · lost 6

GPT-4owon 3 · lost 7

Claude Opus 4won 3 · lost 7

O1won 3 · lost 7

O3won 3 · lost 7

Claude Sonnet 4.5won 3 · lost 7

GPT-5 Miniwon 3 · lost 7

GPT-4.1won 3 · lost 7

Claude 3 Opuswon 2 · lost 5

Inklingwon 2 · lost 7

GPT-5.2won 2 · lost 7

Grok 4.6won 2 · lost 7

Claude Opus 5won 2 · lost 7

GPT-4 Turbowon 2 · lost 8

GPT-5won 2 · lost 8

GPT-5.1won 2 · lost 8

Foundation Sec 8B Instructwon 1 · lost 5

Meta SecAlign 8Bwon 1 · lost 5

Apriel 1.5 15B Thinkerwon 1 · lost 5

Mistral NeMo Minitron 8B Instructwon 1 · lost 5

Phi 4won 1 · lost 5

Claude Opus 4.7won 1 · lost 8

Claude Opus 5.5won 1 · lost 8

Muse Spark 1.1won 1 · lost 8

MiniMax M2won 0 · lost 6

Claude Sonnet 5won 0 · lost 9

Grok 4.7won 0 · lost 9

Claude Opus 4.8won 0 · lost 9

§ 3 · Sources

Where the numbers come from

3 publications, 13 figures. Every one links to the page it was read from.

Vals.ai ↗2 measuresread 2026-09-26

Vals · LegalBench 79.4%Vals · MedQA 77.39%

HELM Safety ↗5 measuresread 2026-09-26

HELM Safety · HarmBench 72.8%HELM Safety · SimpleSafetyTests 100%HELM Safety · Anthropic Red Team 99.6%HELM Safety · BBQ 95.4%HELM Safety · XSTest 97.9%

Enkrypt AI Safety Leaderboard ↗6 measuresread 2026-09-26

Enkrypt · Jailbreak risk 7.4%Enkrypt · Harmful content risk 28.3%Enkrypt · CBRN risk 8.8%Enkrypt · Toxicity risk 2.2%Enkrypt · Bias risk 44.2%Enkrypt · Insecure code risk 30.2%

Badge

[![PublicAI Index](https://publicai.io/model-index/badge?model=qwen-2-5-instruct-turbo-72b)](https://publicai.io/model-index/m/qwen-2-5-instruct-turbo-72b)