IFScale
Models write business reports while including up to 500 specified keywords. The benchmark measures how many instructions they follow at each density.
The authors report 20 models from seven providers. Arize independently repeated the evaluation on newer models.
- Made by
- Distyl AI
- Released
- July 2025
- Kind
- Following precise instructions
- Level
- University
- Scored
- Checked automatically
- Answers
- Open-ended
- Tasks
- All public
- Measures
- Capability
- Subject
- Economics and business
- Language
- English
- Interaction
- Single turn
- Refresh
- One fixed set
- Run by
- Anyone
- In views
- Law and finance
- Strongest model tested
- o3 #84 on the capability index
- Last model added
- September 2025
- Scores refreshed
- November 21st, 2026
Gemini 2.5 Pro leads with 68.9% among models released by September 2025 Gemini 2.5 Pro leads with 68.9% among models released by September 2025
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. 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 2025, 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
- 68.9
Gemini 2.5 Pro
- 62.8 o3
- 61.9 Grok 3
- 52.7 Claude 3.7 Sonnet
- 52.1 claude-opus-4 (r)
- 48.9 GPT-4.1
- 44.6 Claude Opus 4
- 43.0 GPT-4.5
- 42.9 Claude Sonnet 4
- 39.9 claude-sonnet-4 (r)
- 36.4 Grok-3 mini
- 34.4 o4-mini
- 34.2
Gemini 2.5 Flash
- 30.9
DeepSeek-R1
- 27.7
Llama 4 Maverick
- 27.2 GPT-4.1 mini
- 20.9
Qwen3-235B-A22B
- 16.2 GPT-4.1 nano
- 15.4 GPT-4o
- 10.4 GPT-4o mini
- 8.50 Claude 3.5 Haiku
- 6.70
Llama 4 Scout
- 1
Gemini 2.5 Pro Jun 2025 68.9%
- 2 o3 high 62.8%
- 3 Grok 3 61.9%
- 4 Claude 3.7 Sonnet 52.7%
- 5 claude-opus-4 (r) 52.1%
- 6 GPT-4.1 48.9%
- 7 Claude Opus 4 44.6%
- 8 GPT-4.5 43%
- 9 Claude Sonnet 4 42.9%
- 10 claude-sonnet-4 (r) 39.9%
- 11 Grok-3 mini 36.4%
- 12 o4-mini medium 34.4%
- 13
Gemini 2.5 Flash Sep 2025 34.2%
- 14
DeepSeek-R1 May 2025 30.9%
- 15
Llama 4 Maverick 27.7%
- 16 GPT-4.1 mini 27.2%
- 17
Qwen3-235B-A22B 20.9%
- 18 GPT-4.1 nano 16.2%
- 19 GPT-4o Mar 2025 15.4%
- 20 GPT-4o mini 10.4%
- 21 Claude 3.5 Haiku 8.50%
- 22
Llama 4 Scout 6.70%
Source: The IFScale paper
- 68.9
Gemini 2.5 Pro
- 62.8 o3
- 61.9 Grok 3
- 52.7 Claude 3.7 Sonnet
- 48.9 GPT-4.1
- 44.6 Claude Opus 4
- 43.0 GPT-4.5
- 42.9 Claude Sonnet 4
- 36.4 Grok-3 mini
- 34.4 o4-mini
- 34.2
Gemini 2.5 Flash
- 30.9
DeepSeek-R1
- 27.7
Llama 4 Maverick
- 27.2 GPT-4.1 mini
- 20.9
Qwen3-235B-A22B
- 16.2 GPT-4.1 nano
- 15.4 GPT-4o
- 10.4 GPT-4o mini
- 8.50 Claude 3.5 Haiku
- 6.70
Llama 4 Scout
- 1
Gemini 2.5 Pro Jun 2025 68.9%
- 2 o3 high 62.8%
- 3 Grok 3 61.9%
- 4 Claude 3.7 Sonnet 52.7%
- 5 GPT-4.1 48.9%
- 6 Claude Opus 4 44.6%
- 7 GPT-4.5 43%
- 8 Claude Sonnet 4 42.9%
- 9 Grok-3 mini 36.4%
- 10 o4-mini medium 34.4%
- 11
Gemini 2.5 Flash Sep 2025 34.2%
- 12
DeepSeek-R1 May 2025 30.9%
- 13
Llama 4 Maverick 27.7%
- 14 GPT-4.1 mini 27.2%
- 15
Qwen3-235B-A22B 20.9%
- 16 GPT-4.1 nano 16.2%
- 17 GPT-4o Mar 2025 15.4%
- 18 GPT-4o mini 10.4%
- 19 Claude 3.5 Haiku 8.50%
- 20
Llama 4 Scout 6.70%
Source: The IFScale paper
| # | Entry | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | | 68.9% | Jun 2025 | Official leaderboard | |
| 2 | o3 | 62.8% | high | Apr 2025 | Official leaderboard |
| 3 | Grok 3 | 61.9% | Apr 2025 | Official leaderboard | |
| 4 | Claude 3.7 Sonnet | 52.7% | Feb 2025 | Official leaderboard | |
| 5 | claude-opus-4 (r) | 52.1% | Official leaderboard | ||
| 6 | GPT-4.1 | 48.9% | Apr 2025 | Official leaderboard | |
| 7 | Claude Opus 4 | 44.6% | May 2025 | Official leaderboard | |
| 8 | GPT-4.5 | 43% | Feb 2025 | Official leaderboard | |
| 9 | Claude Sonnet 4 | 42.9% | May 2025 | Official leaderboard | |
| 10 | claude-sonnet-4 (r) | 39.9% | Official leaderboard | ||
| 11 | Grok-3 mini | 36.4% | Apr 2025 | Official leaderboard | |
| 12 | o4-mini | 34.4% | medium | Apr 2025 | Official leaderboard |
| 13 | | 34.2% | Sep 2025 | Official leaderboard | |
| 14 | | 30.9% | May 2025 | Official leaderboard | |
| 15 | | 27.7% | Apr 2025 | Official leaderboard | |
| 16 | GPT-4.1 mini | 27.2% | Apr 2025 | Official leaderboard | |
| 17 | | 20.9% | Apr 2025 | Official leaderboard | |
| 18 | GPT-4.1 nano | 16.2% | Apr 2025 | Official leaderboard | |
| 19 | GPT-4o Mar 2025 | 15.4% | Mar 2025 | Official leaderboard | |
| 20 | GPT-4o mini | 10.4% | Jul 2024 | Official leaderboard | |
| 21 | Claude 3.5 Haiku | 8.50% | Oct 2024 | Official leaderboard | |
| 22 | | 6.70% | Apr 2025 | Official leaderboard |
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | | 68.9% | Jun 2025 | Official leaderboard | |
| 2 | o3 | 62.8% | high | Apr 2025 | Official leaderboard |
| 3 | Grok 3 | 61.9% | Apr 2025 | Official leaderboard | |
| 4 | Claude 3.7 Sonnet | 52.7% | Feb 2025 | Official leaderboard | |
| 5 | GPT-4.1 | 48.9% | Apr 2025 | Official leaderboard | |
| 6 | Claude Opus 4 | 44.6% | May 2025 | Official leaderboard | |
| 7 | GPT-4.5 | 43% | Feb 2025 | Official leaderboard | |
| 8 | Claude Sonnet 4 | 42.9% | May 2025 | Official leaderboard | |
| 9 | Grok-3 mini | 36.4% | Apr 2025 | Official leaderboard | |
| 10 | o4-mini | 34.4% | medium | Apr 2025 | Official leaderboard |
| 11 | | 34.2% | Sep 2025 | Official leaderboard | |
| 12 | | 30.9% | May 2025 | Official leaderboard | |
| 13 | | 27.7% | Apr 2025 | Official leaderboard | |
| 14 | GPT-4.1 mini | 27.2% | Apr 2025 | Official leaderboard | |
| 15 | | 20.9% | Apr 2025 | Official leaderboard | |
| 16 | GPT-4.1 nano | 16.2% | Apr 2025 | Official leaderboard | |
| 17 | GPT-4o Mar 2025 | 15.4% | Mar 2025 | Official leaderboard | |
| 18 | GPT-4o mini | 10.4% | Jul 2024 | Official leaderboard | |
| 19 | Claude 3.5 Haiku | 8.50% | Oct 2024 | Official leaderboard | |
| 20 | | 6.70% | Apr 2025 | Official leaderboard |
Rankings by part
We read 4 parts from the benchmark’s paper, each ranking models on one part of the test, such as 10 instructions, 50 instructions and 100 instructions. Grok 3 leads 2 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.
10 instructions
20 models we track have a score here.
- 1 Claude 3.7 Sonnet ↑3 100%
- 2 GPT-4.5 ↑5 100%
- 3
Llama 4 Maverick ↑10 100%
- 4
Llama 4 Scout ↑16 100%
- 5 Grok 3 ↓2 100%
- 6 Grok-3 mini ↑3 100%
- 7 GPT-4.1 mini ↑7 100%
- 8 o3 ↓6 100%
- 9 o4-mini ↑1 100%
- 10
Qwen3-235B-A22B ↑5 100%
50 instructions
20 models we track have a score here.
- 1 Grok 3 ↑2 100%
- 2 Claude Opus 4 ↑4 100%
- 3 Claude 3.7 Sonnet ↑1 99.6%
- 4 o3 ↓2 99.6%
- 5 o4-mini ↑5 99.6%
- 6
Gemini 2.5 Pro Jun 2025 ↓5 99.6%
- 7 Grok-3 mini ↑2 99.2%
- 8 GPT-4.1 ↓3 98.8%
- 9 Claude Sonnet 4 ↓1 98%
- 10
Gemini 2.5 Flash Sep 2025 ↑1 96%
100 instructions
20 models we track have a score here.
- 1 Grok 3 ↑2 98.8%
- 2 o3 98.4%
- 3
Gemini 2.5 Pro Jun 2025 ↓2 98.4%
- 4 o4-mini ↑6 97.8%
- 5 GPT-4.1 95.4%
- 6 Claude 3.7 Sonnet ↓2 94.8%
- 7 Claude Opus 4 ↓1 94.6%
- 8 Claude Sonnet 4 94.4%
- 9 Grok-3 mini 92.8%
- 10 GPT-4.5 ↓3 90.8%
250 instructions
20 models we track have a score here.
- 1 o3 ↑1 97.8%
- 2 o4-mini ↑8 86.8%
- 3 Grok 3 86.2%
- 4
Gemini 2.5 Pro Jun 2025 ↓3 84.8%
- 5 Claude Sonnet 4 ↑3 77.2%
- 6 GPT-4.1 ↓1 74%
- 7 Claude 3.7 Sonnet ↓3 72.9%
- 8 Claude Opus 4 ↓2 67.9%
- 9 GPT-4.5 ↓2 65%
- 10 Grok-3 mini ↓1 56.6%
Number one over time
Lab claims count from the day the card came out, independent runs from the model’s release.
Source: The IFScale 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 IFScale 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
- 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 14 months ago, in September 2025, for Gemini 2.5 Flash. 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 (22 entries).
- Pass Models scored 20 models we track, plus 2 other entries on its leaderboard.
- Warning Newest score The newest came 14 months ago, in September 2025, for Gemini 2.5 Flash.
- Note Frontier models None of the top 10 has a score. The strongest tested is o3 (#84).
- Pass Headroom The best is 68.9%, under 85%, so it still separates models.
Leaderboard import 3 pass
- Pass Importer We read the board on distylai.github.io: 21 rows for models we track and 2 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.