Instruction Following · Benchmark profile

Instruction-Following Eval

A benchmark of 541 prompts built from 25 verifiable instruction types. It tests whether a model follows checkable constraints such as keyword, length, casing, and response-format requirements.

Reference2023Active24 models

Data verified 21 Jul 2026 · Methodology 1.6.0

Benchmark score on Instruction-Following Eval

Leaderboard · 24 models

Qwen3.5 27B leads at 95%, followed by Agents-A1 (94.8%) and Qwen3.7-Plus (94.6%).

Display onlyInstruction Following2023

#1Open

Qwen3.5 27B

Alibaba Cloud

qwen3.5-27b

95%

Overall #84 · Context 262K tokens

#2Open

Agents-A1

InternScience

agents-a1

94.8%

Overall — · Context 262K tokens

#3Closed

Qwen3.7-Plus

Alibaba Cloud

qwen3.7-plus

94.6%

Overall #20 · Context 1M tokens

Visual analysis

See the field.

Switch between model placement, score distribution and descriptive provider averages. Every view uses the same sourced leaderboard.

ViewModelsColours

Alibaba CloudInternScienceMoonshot AIOpenAIZ.AILiquidAIAnthropicDeepSeekZyphraOpenBMB

Instruction-Following Eval leaderboard

20 ranked models · higher is better

View accessible chart data

Accessible data for Instruction-Following Eval leaderboard
Model	Rank	Provider	Score
Qwen3.5 27B	#1	Alibaba Cloud	95%
Agents-A1	#2	InternScience	94.8%
Qwen3.7-Plus	#3	Alibaba Cloud	94.6%
Qwen3.6 Plus	#4	Alibaba Cloud	94.3%
Qwen3.7-Max	#5	Alibaba Cloud	94.3%
Kimi K2.5	#6	Moonshot AI	93.9%
o3-mini	#7	OpenAI	93.9%
Qwen3.5-122B-A10B	#8	Alibaba Cloud	93.4%
GLM-5	#9	Z.AI	92.6%
Qwen3.5 397B	#10	Alibaba Cloud	92.6%
o1	#11	OpenAI	92.2%
Qwen3.5-35B-A3B	#12	Alibaba Cloud	91.9%
LFM2.5-8B-A1B	#13	LiquidAI	91.8%
Claude Opus 4.5	#14	Anthropic	90.9%
GPT-4.1 mini	#15	OpenAI	88.5%
GPT-4.1	#16	OpenAI	87.4%
DeepSeek V3	#17	DeepSeek	86.1%
ZAYA1-8B	#18	Zyphra	85.6%
GPT-4.1 nano	#19	OpenAI	83.2%
MiniCPM5-1B	#20	OpenBMB	80.4%

Benchmark score table (24 models)

One best score per model · higher is better

Instruction-Following Eval leaderboard ranked by score
Rank	Model	Provider	License	Evidence use	Score
#1	Qwen3.5 27B qwen3.5-27b	Alibaba Cloud	open	Reference only	95%
#2	Agents-A1 agents-a1	InternScience	open	Estimated reference	94.8%
#3	Qwen3.7-Plus qwen3.7-plus	Alibaba Cloud	—	Reference only	94.6%
#4	Qwen3.6 Plus qwen3-6-plus	Alibaba Cloud	closed	Reference only	94.3%
#5	Qwen3.7-Max qwen3.7-max	Alibaba Cloud	—	Reference only	94.3%
#6	Kimi K2.5 kimi-k2.5	Moonshot AI	—	Reference only	93.9%
#7	o3-mini o3-mini	OpenAI	closed	Reference only	93.9%
#8	Qwen3.5-122B-A10B qwen3-5-122b-a10b	Alibaba Cloud	open	Reference only	93.4%
#9	GLM-5 glm-5	Z.AI	open	Reference only	92.6%
#10	Qwen3.5 397B qwen3.5-397b-a17b	Alibaba Cloud	open	Estimated reference	92.6%
#11	o1 o1	OpenAI	closed	Estimated reference	92.2%
#12	Qwen3.5-35B-A3B qwen3-5-35b-a3b	Alibaba Cloud	open	Reference only	91.9%
#13	LFM2.5-8B-A1B lfm2-5-8b-a1b	LiquidAI	open	Estimated reference	91.8%
#14	Claude Opus 4.5 claude-opus-4-5	Anthropic	closed	Reference only	90.9%
#15	GPT-4.1 mini gpt-4-1-mini	OpenAI	closed	Estimated reference	88.5%
#16	GPT-4.1 gpt-4-1	OpenAI	closed	Reference only	87.4%
#17	DeepSeek V3 deepseek-v3	DeepSeek	open	Reference only	86.1%
#18	ZAYA1-8B zaya1-8b	Zyphra	open	Estimated reference	85.6%
#19	GPT-4.1 nano gpt-4-1-nano	OpenAI	closed	Estimated reference	83.2%
#20	MiniCPM5-1B minicpm5-1b	OpenBMB	open	Estimated reference	80.4%
#21	Mellum2-12B-A2.5B-Thinking mellum2-12b-a2-5b-thinking	JetBrains	open	Estimated reference	76.5%
#22	Mellum2-12B-A2.5B-Instruct mellum2-12b-a2-5b-instruct	JetBrains	open	Estimated reference	75.8%
#23	LFM2.5-230M lfm2-5-230m	LiquidAI	open	Estimated reference	71.7%
#24	LFM2.5-VL-450M lfm2-5-vl-450m	LiquidAI	open	Estimated reference	61.2%

The top of this snapshot is led by Qwen3.5 27B at 95%; third place is 0.40 points behind. The top-10 spread is 2.4 points.

Compare top models

Qwen3.5 27B vs Agents-A1 Agents-A1 vs Qwen3.7-Plus Qwen3.7-Plus vs Qwen3.6 Plus Qwen3.6 Plus vs Qwen3.7-Max

About Instruction-Following Eval

Definition and scoring

Organisation: Jeffrey Zhou, Tianjian Lu, Swaroop Mishra, Siddhartha Brahma, Sujoy Basu, Yi Luan, Denny Zhou, Le Hou
Category: Instruction Following
Version: 2023
Direction: higher is better
Ranking use: Reference
Contamination risk: Unknown

A benchmark of 541 prompts built from 25 verifiable instruction types. It tests whether a model follows checkable constraints such as keyword, length, casing, and response-format requirements. Results stay tied to the exact model variant and evaluation system. Multiple systems for the same model use the best published score on this page; overall Lumina scoring uses the median of ranking-eligible rows.

Open benchmark source ↗

FAQ

Quick answers

What does Instruction-Following Eval measure?

A benchmark of 541 prompts built from 25 verifiable instruction types. It tests whether a model follows checkable constraints such as keyword, length, casing, and response-format requirements.

Which model scores highest on Instruction-Following Eval?

Qwen3.5 27B by Alibaba Cloud currently leads with 95%.

How many models are evaluated on Instruction-Following Eval?

24 models in the LuminaBench cohort have a qualifying score on this benchmark.

Does this affect overall Lumina rank?

No. This benchmark is display-only and does not enter the overall Lumina composite.

IFEval

Rolling · 37 results · Not Weighted

Arena-Hard-Auto

Rolling · 1 results · Not Weighted

WildBench

Rolling · Not evaluated · Not Weighted

IFBench

Rolling · 214 results · Not Weighted

Arena-Hard v2

v2 · Not evaluated · Reference

EQ-Bench

3 · Not evaluated · Reference

Instruction Following · Benchmark profile

Instruction-Following Eval

A benchmark of 541 prompts built from 25 verifiable instruction types. It tests whether a model follows checkable constraints such as keyword, length, casing, and response-format requirements.

Reference2023Active24 models

Data verified 21 Jul 2026 · Methodology 1.6.0

Benchmark score on Instruction-Following Eval

Leaderboard · 24 models

Qwen3.5 27B leads at 95%, followed by Agents-A1 (94.8%) and Qwen3.7-Plus (94.6%).

Display onlyInstruction Following2023

#1Open

Qwen3.5 27B

Alibaba Cloud

qwen3.5-27b

95%

Overall #84 · Context 262K tokens

#2Open

Agents-A1

InternScience

agents-a1

94.8%

Overall — · Context 262K tokens

#3Closed

Qwen3.7-Plus

Alibaba Cloud

qwen3.7-plus

94.6%

Overall #20 · Context 1M tokens

Visual analysis

See the field.

Switch between model placement, score distribution and descriptive provider averages. Every view uses the same sourced leaderboard.

ViewModelsColours

Alibaba CloudInternScienceMoonshot AIOpenAIZ.AILiquidAIAnthropicDeepSeekZyphraOpenBMB

Instruction-Following Eval leaderboard

20 ranked models · higher is better

View accessible chart data

Accessible data for Instruction-Following Eval leaderboard
Model	Rank	Provider	Score
Qwen3.5 27B	#1	Alibaba Cloud	95%
Agents-A1	#2	InternScience	94.8%
Qwen3.7-Plus	#3	Alibaba Cloud	94.6%
Qwen3.6 Plus	#4	Alibaba Cloud	94.3%
Qwen3.7-Max	#5	Alibaba Cloud	94.3%
Kimi K2.5	#6	Moonshot AI	93.9%
o3-mini	#7	OpenAI	93.9%
Qwen3.5-122B-A10B	#8	Alibaba Cloud	93.4%
GLM-5	#9	Z.AI	92.6%
Qwen3.5 397B	#10	Alibaba Cloud	92.6%
o1	#11	OpenAI	92.2%
Qwen3.5-35B-A3B	#12	Alibaba Cloud	91.9%
LFM2.5-8B-A1B	#13	LiquidAI	91.8%
Claude Opus 4.5	#14	Anthropic	90.9%
GPT-4.1 mini	#15	OpenAI	88.5%
GPT-4.1	#16	OpenAI	87.4%
DeepSeek V3	#17	DeepSeek	86.1%
ZAYA1-8B	#18	Zyphra	85.6%
GPT-4.1 nano	#19	OpenAI	83.2%
MiniCPM5-1B	#20	OpenBMB	80.4%

Benchmark score table (24 models)

One best score per model · higher is better

Instruction-Following Eval leaderboard ranked by score
Rank	Model	Provider	License	Evidence use	Score
#1	Qwen3.5 27B qwen3.5-27b	Alibaba Cloud	open	Reference only	95%
#2	Agents-A1 agents-a1	InternScience	open	Estimated reference	94.8%
#3	Qwen3.7-Plus qwen3.7-plus	Alibaba Cloud	—	Reference only	94.6%
#4	Qwen3.6 Plus qwen3-6-plus	Alibaba Cloud	closed	Reference only	94.3%
#5	Qwen3.7-Max qwen3.7-max	Alibaba Cloud	—	Reference only	94.3%
#6	Kimi K2.5 kimi-k2.5	Moonshot AI	—	Reference only	93.9%
#7	o3-mini o3-mini	OpenAI	closed	Reference only	93.9%
#8	Qwen3.5-122B-A10B qwen3-5-122b-a10b	Alibaba Cloud	open	Reference only	93.4%
#9	GLM-5 glm-5	Z.AI	open	Reference only	92.6%
#10	Qwen3.5 397B qwen3.5-397b-a17b	Alibaba Cloud	open	Estimated reference	92.6%
#11	o1 o1	OpenAI	closed	Estimated reference	92.2%
#12	Qwen3.5-35B-A3B qwen3-5-35b-a3b	Alibaba Cloud	open	Reference only	91.9%
#13	LFM2.5-8B-A1B lfm2-5-8b-a1b	LiquidAI	open	Estimated reference	91.8%
#14	Claude Opus 4.5 claude-opus-4-5	Anthropic	closed	Reference only	90.9%
#15	GPT-4.1 mini gpt-4-1-mini	OpenAI	closed	Estimated reference	88.5%
#16	GPT-4.1 gpt-4-1	OpenAI	closed	Reference only	87.4%
#17	DeepSeek V3 deepseek-v3	DeepSeek	open	Reference only	86.1%
#18	ZAYA1-8B zaya1-8b	Zyphra	open	Estimated reference	85.6%
#19	GPT-4.1 nano gpt-4-1-nano	OpenAI	closed	Estimated reference	83.2%
#20	MiniCPM5-1B minicpm5-1b	OpenBMB	open	Estimated reference	80.4%
#21	Mellum2-12B-A2.5B-Thinking mellum2-12b-a2-5b-thinking	JetBrains	open	Estimated reference	76.5%
#22	Mellum2-12B-A2.5B-Instruct mellum2-12b-a2-5b-instruct	JetBrains	open	Estimated reference	75.8%
#23	LFM2.5-230M lfm2-5-230m	LiquidAI	open	Estimated reference	71.7%
#24	LFM2.5-VL-450M lfm2-5-vl-450m	LiquidAI	open	Estimated reference	61.2%

The top of this snapshot is led by Qwen3.5 27B at 95%; third place is 0.40 points behind. The top-10 spread is 2.4 points.

Compare top models

Qwen3.5 27B vs Agents-A1 Agents-A1 vs Qwen3.7-Plus Qwen3.7-Plus vs Qwen3.6 Plus Qwen3.6 Plus vs Qwen3.7-Max

About Instruction-Following Eval

Definition and scoring

Organisation: Jeffrey Zhou, Tianjian Lu, Swaroop Mishra, Siddhartha Brahma, Sujoy Basu, Yi Luan, Denny Zhou, Le Hou
Category: Instruction Following
Version: 2023
Direction: higher is better
Ranking use: Reference
Contamination risk: Unknown

Open benchmark source ↗

FAQ

Quick answers

What does Instruction-Following Eval measure?

A benchmark of 541 prompts built from 25 verifiable instruction types. It tests whether a model follows checkable constraints such as keyword, length, casing, and response-format requirements.

Which model scores highest on Instruction-Following Eval?

Qwen3.5 27B by Alibaba Cloud currently leads with 95%.

How many models are evaluated on Instruction-Following Eval?

24 models in the LuminaBench cohort have a qualifying score on this benchmark.

Does this affect overall Lumina rank?

No. This benchmark is display-only and does not enter the overall Lumina composite.

IFEval

Rolling · 37 results · Not Weighted

Arena-Hard-Auto

Rolling · 1 results · Not Weighted

WildBench

Rolling · Not evaluated · Not Weighted

IFBench

Rolling · 214 results · Not Weighted

Arena-Hard v2

v2 · Not evaluated · Reference

EQ-Bench

3 · Not evaluated · Reference

Search LUMINA BENCH

Navigation

Instruction-Following Eval

Leaderboard · 24 models

Qwen3.5 27B

Agents-A1

Qwen3.7-Plus

See the field.

Instruction-Following Eval leaderboard

Crop Instruction-Following Eval leaderboard

Benchmark score table (24 models)

Crop Instruction-Following Eval benchmark table

Compare top models

Definition and scoring

Quick answers

What does Instruction-Following Eval measure?

Which model scores highest on Instruction-Following Eval?

How many models are evaluated on Instruction-Following Eval?

Does this affect overall Lumina rank?

Instruction-Following Eval

Leaderboard · 24 models

Qwen3.5 27B

Agents-A1

Qwen3.7-Plus

See the field.

Instruction-Following Eval leaderboard

Crop Instruction-Following Eval leaderboard

Benchmark score table (24 models)

Crop Instruction-Following Eval benchmark table

Compare top models

Definition and scoring

Quick answers

What does Instruction-Following Eval measure?

Which model scores highest on Instruction-Following Eval?

How many models are evaluated on Instruction-Following Eval?

Does this affect overall Lumina rank?

Leaderboard · 24 models

Qwen3.5 27B

Agents-A1

Qwen3.7-Plus

See the field.

Benchmark score table (24 models)

Compare top models

Definition and scoring

Quick answers

What does Instruction-Following Eval measure?

Which model scores highest on Instruction-Following Eval?

How many models are evaluated on Instruction-Following Eval?

Does this affect overall Lumina rank?

More Instruction Following benchmarks

Leaderboard · 24 models

Qwen3.5 27B

Agents-A1

Qwen3.7-Plus

See the field.

Benchmark score table (24 models)

Compare top models

Definition and scoring

Quick answers

What does Instruction-Following Eval measure?

Which model scores highest on Instruction-Following Eval?

How many models are evaluated on Instruction-Following Eval?

Does this affect overall Lumina rank?

More Instruction Following benchmarks