Skip to content
VECTOR WIREAI INTELLIGENCE
UTC

IFEval leaderboard — the family board.

3 TRACKED VARIANTS · 2 FIRST-CLASS BOARDS

One family, 3 tracked prints: IFEval (HF Open LLM) is cited standalone and keeps live board of its own. Scoring configs and splits of the base board render as sections of this page, each under its own honest label.

● LIVE DATA110 MODELS ON THIS BOARDLEADER QWEN3.5 27B AT 95

First-class boards in this familyCITED STANDALONE · EACH KEEPS ITS OWN LIVE BOARD

#BoardModels scored
01IFEvalTHIS PAGE110

The board — IFEvalTOP 100 OF 110 MEASURED · BEST SCORE PER MODEL, DEFAULT VARIANT

#ModelVendorScoreVLast seen
01Qwen3.5 27BAlibaba952026-08-23
02Qwen3.7 Plus PreviewAlibaba94.62026-08-23
03Qwen3.6 PlusAlibaba94.32026-08-23
04Qwen3.7 MaxAlibaba94.32026-08-23
05o3-miniOpenAI93.92026-08-23
06Qwen3.5 122B A10BAlibaba93.42026-08-23
07Claude 3.7 SonnetAnthropic93.22026-08-23
08Qwen3.5 397B A17BAlibaba92.62026-08-23
09Llama 3.3 70B InstructMeta92.12026-08-23
10Nova ProAmazon92.12026-08-23
11Qwen3.5 35B A3BAlibaba91.92026-08-23
12LFM2.5-8B-A1BLiquid AI91.82026-08-09
13Qwen3.5 9BAlibaba91.52026-08-23
14Gemma 4 26B A4BGoogle91.42026-08-09
15Qwen3 30B A3B 2507 ThinkingAlibaba90.82026-08-09
16Gemma 3 27BGoogle90.42026-08-23
17NVIDIA Nemotron Nano 9B V2NVIDIA90.32026-08-23
18Gemma 3 4BGoogle90.22026-10-07
19Claude 3.5 SonnetAnthropic90.12026-06-12
20Qwen3.5 4BAlibaba89.82026-09-17
21Kimi K2 InstructMoonshot89.82026-08-23
22Nova LiteAmazon89.72026-08-23
23EXAONE 4.5 33BLG AI89.62026-08-26
25Gemini 1.5 ProGoogle89.42026-06-12
26MiniMax Text 01MiniMax89.12026-06-12
27Gemma 3 12BGoogle88.92026-08-23
28Qwen3 Next 80B A3BAlibaba88.92026-08-23
29Qwen3 235B A22B Instruct 2507Alibaba88.72026-08-23
30Llama 3.1 Instruct 405BMeta88.62026-09-11
31LFM2.5-1.2B-ThinkingLiquid AI88.42026-08-09
32Qwen3 32BAlibaba88.42026-06-15
33Gemini 2.0 Flash ExpGoogle88.42026-06-12
34Qwen3 VL 235B A22B ReasoningAlibaba88.22026-08-23
35GPT-4.5 PreviewOpenAI88.22026-08-23
36Gemma 4 E4BGoogle87.92026-09-10
37Qwen3 VL 32B ReasoningAlibaba87.82026-08-23
38Qwen3 VL 235B A22B InstructAlibaba87.82026-08-23
39Qwen3 Next 80B A3B InstructAlibaba87.62026-08-23
40Claude Sonnet 4Anthropic87.62026-06-15
41Llama 3.1 70B InstructMeta87.52026-08-23
42Claude Opus 4Anthropic87.42026-06-15
43GPT-4.1OpenAI87.42026-08-23
44DeepSeek-V3DeepSeek87.32026-08-23
45Qwen2.5 Instruct 72BAlibaba87.22026-08-23
46Nova MicroAmazon87.22026-08-23
47gpt-oss-20bOpenAI86.72026-08-09
48LFM2.5-1.2B-InstructLiquid AI86.22026-08-09
49Seed Oss 36B InstructByteDance85.82026-06-15
50Qwen3 VL 30B A3B InstructAlibaba85.82026-08-23
51Qwen3 4B 2507 InstructAlibaba85.62026-10-07
52Hunyuan Large InstructTencent852026-05-31
53Phi 4 Reasoning PlusMicrosoft84.92026-08-23
54o1-miniOpenAI84.82026-06-05
55Sarvam 105BSarvam AI84.82026-08-23
56Qwen3 VL 32B InstructAlibaba84.72026-08-23
57GPT-4oOpenAI84.32026-08-23
58GPT-4.1 miniOpenAI84.12026-08-23
59QwQ 32B PreviewAlibaba83.92026-08-23
60Qwen3 VL 8B InstructAlibaba83.72026-08-23
61DeepSeek-R1DeepSeek83.32026-06-04
62Qwen3 235B A22BAlibaba83.22026-06-15
63Qwen3 VL Thinking (8B)Alibaba83.22026-08-23
64Gemma 4 E2BGoogle832026-09-10
65Qwen3 VL 4B (Reasoning)Alibaba82.62026-08-23
66LFM2.5-VL-3BLiquid AI82.32026-08-23
67Qwen3 VL 4B InstructAlibaba82.32026-08-23
68Granite 4.0 H TinyIBM82.22026-10-07
69Qwen3 VL 30B A3B ReasoningAlibaba81.72026-08-23
70DeepSeek-V2.5DeepSeek80.62026-05-03
71Llama 3.1 8B InstructMeta80.42026-08-23
72Gemma 3 1B InstructGoogle80.22026-10-07
73Granite 4.0 H 1BIBM80.12026-08-09
74Granite 4.0 1BIBM79.62026-08-09
75LFM2-2.6BLiquid AI79.62026-10-07
76LFM2-8B-A1B (Non-Reasoning)Liquid AI79.42026-10-07
77Llama 3.1 Nemotron Nano 8B V1NVIDIA79.32026-08-23
78Qwen3.5 2BAlibaba78.62026-09-10
79DeepSeek-R1-Distill-Qwen-14BDeepSeek78.32026-06-05
80Llama 3.2 3B InstructMeta77.42026-10-07
81LFM2.5-350MLiquid AI77.02026-08-09
82North-Micro-Vision-InstructCohere74.92026-08-23
83LFM2-1.2BLiquid AI74.92026-10-07
84Granite 3.3 8B InstructIBM74.82026-08-23
85GPT-4.1 nanoOpenAI74.52026-08-23
86Granite 3.2 8B InstructIBM74.32026-06-11
87Qwen3 1.7BAlibaba74.02026-10-07
88Qwen3 1.7B (instruct)Alibaba73.72026-08-09
89LFM2-VL-3BLiquid AI72.92026-09-10
90LFM2-700MLiquid AI72.22026-10-07
91LFM2.5-230MLiquid AI71.72026-08-09
92Qwen3.5 0.8BAlibaba71.22026-08-23
93Granite 3.3 2B InstructIBM65.82026-06-11
94LFM2-350MLiquid AI65.12026-10-07
95Qwen3 0.6BAlibaba64.22026-10-07
96Granite 3.1 2B InstructIBM63.62026-06-11
97Phi 4Microsoft632026-08-23
98Granite 3.2 2B InstructIBM61.52026-06-11
99LFM2.5-VL-450M-ExtractLiquid AI61.22026-08-09
100MiMo 7B RLXiaomi612026-06-05
◆ IV — INDEPENDENTLY VERIFIED · ◆ AA — AGGREGATOR · ◆ VA — VENDOR · ◇ SA — SOURCE-ATTRIBUTED

Variants of this boardSCORING CONFIGS & SPLITS — NOT CITED STANDALONE, SO THEY LIVE HERE

IFEval (avg)

VARIANT11 models · best score per model
#ModelVendorScoreVLast seen
01Claude 3.5 SonnetAnthropic90.12026-06-06
02Granite 4.1 30BIBM89.72026-06-15
03Gemini 1.5 ProGoogle89.42026-06-06
04MiniMax Text 01MiniMax89.12026-06-06
05Gemini 2.0 Flash ExpGoogle88.42026-06-06
06DeepSeek-V3DeepSeek87.32026-06-06
07Qwen2.5 Instruct 72BAlibaba87.22026-06-06
08Granite 4.1 8BIBM87.12026-06-15
09Llama 3.1 Instruct 405BMeta86.42026-06-06
10GPT-4oOpenAI84.12026-06-06
11Granite 4.1 3BIBM82.32026-06-15
THE FAMILY BOARD · EVERY PRINT LABELED · EVERY SCORE SOURCE-ATTRIBUTED ON ITS OWN LIVE BOARDAll leaderboardsThe frontier boardModels by vendor