Skip to main content
Instruction Following benchmark report

Best LLMs for Instruction FollowingJuly 2026 Leaderboard

As of July 2026, the top instruction following model on the BenchLM leaderboard is MAI-Thinking-1 with a weighted instruction following score of 97.8.

Data refreshed:

Ability to follow precise instructions and constraints

Decision lens: use provisional-ranked mode for broader public evidence and verified-ranked mode for source-only comparisons. A model can move between views as evidence coverage changes.

Data refreshed
July 21, 2026
Provisional-ranked
31 of 290 models
Verified-ranked
31 of 290 models
Weighted evidence
2 of 3 benchmarks
3 tracked benchmarks

IFEval, IFBench, SOB Value Acc

Best Instruction Following picks

BenchLM summaries for instruction following plus the practical tradeoffs users check next: open weights, price, speed, latency, and context.

How BenchLM scores these

IFEval Leaderboard

Primary score: weighted instruction following score. Higher values rank first. Use the Show metric control to change the value shown in each row.

Updated Embed leaderboard

Switch between provisional-ranked and verified-ranked modes to compare the broader public dataset with sourced-only rankings.

Filters
Provisional-ranked mode includes source-unverified non-generated benchmark evidence.P = provisional benchmark row
Rank / modelWeighted Instruction Following
1
MAI-Thinking-1Microsoft · Closed
97.8%
2
Qwen3.5-27BAlibaba · Open weight
93%
3
Agents-A1InternScience · Open weight
93%
4
Nemotron 3 UltraNVIDIA · Open weight
91.9%
5
Qwen3.7 PlusAlibaba · Closed
91.4%
6
Grok 4.3xAI · Closed
91.2%
7
Qwen3.7 MaxAlibaba · Closed
91%
8
Kimi K2.5Moonshot AI · Open weight
90.3%
9
o3-miniOpenAI · Closed
90.3%
10
Qwen3.5-122B-A10BAlibaba · Open weight
88.9%
11
InklingThinking Machines Lab · Open weight
88.6%
12
GLM-5Z.AI · Open weight
86.5%
13
Qwen3.5 397BAlibaba · Open weight
86.5%
14
Qwen3.6 PlusAlibaba · Closed
86.4%
15
o1OpenAI · Closed
85.4%
16
Qwen3.5-35B-A3BAlibaba · Open weight
84.5%
17
Gemini 3.5 FlashGoogle · Closed
82.4%
18
Nemotron 3 Nano Omni 30B A3BNVIDIA · Open weight
78.7%
19
GPT-4.1 miniOpenAI · Closed
74.6%
20
GPT-4.1OpenAI · Closed
71.4%
21
GPT-4.1 nanoOpenAI · Closed
59.1%
22
Hy3 PreviewTencent · Open weight
59%
23
Claude Opus 4.5Anthropic · Closed
56.4%
24
LFM2.5-8B-A1BLiquidAI · Open weight
55.7%
25
Ling 2.6 FlashInclusionAI · Open weight
48.2%

Top AI Models for Instruction FollowingJuly 2026

As of July 2026, MAI-Thinking-1 leads the provisional instruction following leaderboard with a score of 97.8%, followed by Qwen3.5-27B (93.0%) and Agents-A1 (93.0%). BenchLM is currently showing 31 provisional-ranked models and 31 verified-ranked models in this category.

What changed

Claude Mythos Preview leads IFEval with the highest instruction-following accuracy.

GPT-5.4 close second on IFEval and IFBench.

Claude Opus 4.6 holds #3, with strong IFBench scores.

Top models by benchmark

Tests ability to follow verifiable instructions like format constraints and content requirements(35% of category score)

RankModelReported score
2Agents-A1~94.82

Score in Context

What these scores mean

Instruction following carries a 5% weight in overall scoring — small, but it directly measures reliability. A model that ignores formatting rules, word count limits, or inclusion constraints is unusable in automated pipelines. The weighted score blends IFEval (verifiable constraints) and IFBench.

Known limitations

IFEval tests a specific set of verifiable constraints (word count, formatting, inclusion/exclusion) — it doesn't capture the full range of instruction-following quality. A model can score well on IFEval but still misinterpret nuanced or ambiguous instructions. IFBench is newer and coverage is still building.

How we weight

Instruction following carries a 5% weight in BenchLM.ai's overall scoring. While a smaller category, it directly measures reliability — a model that ignores constraints is unusable in production pipelines. See the instruction following leaderboard.

Leaderboards exclude benchmark rows that BenchLM generated from other scores or cloned from reference models. When a weighted benchmark is missing after that filter, the category falls back to the remaining trustworthy public rows instead of filling the gap with synthetic values.

The full scoring rules, freshness handling, and runtime/pricing caveats live on the BenchLM methodology page.

Scroll horizontally to read the full evidence ledger.

Instruction Following benchmark weights, ranking status, and descriptions
BenchmarkWeightStatusDescription
IFEval35%WeightedTests ability to follow verifiable instructions like format constraints and content requirements
IFBench65%WeightedInstruction-following benchmark used in first-party comparison charts for agent-oriented reasoning models.
SOB Value AccDisplay onlyA structured-output benchmark from Interfaze measuring whether extracted JSON leaf values exactly match verified ground truth.

About Instruction Following Benchmarks

Tests ability to follow verifiable instructions like format constraints and content requirements

Common questions

What is the best LLM for instruction following?

The best instruction-following LLMs are ranked by benchmarks like IFEval, which measure how accurately models adhere to specific formatting, length, and content constraints.

What is IFEval and how does it work?

IFEval (Instruction Following Evaluation) tests whether LLMs can precisely follow verifiable instructions such as word count limits, formatting rules, and inclusion/exclusion constraints.

Why is instruction following important for LLMs?

Instruction following is critical because real-world applications require models to reliably adhere to user specifications, output formats, and constraints rather than just generating plausible text.

Instruction following updates

Instruction following scores just got interesting. Get the weekly update.

One email each week. Unsubscribe anytime.

Related