VECTOR WIREAI INTELLIGENCE
NVDA$1,847+3.2%MSFT$512+1.1%GOOGL$199-0.4%META$728+2.7%AMD$184-1.2%TSM$212+0.6%PLTR$98+4.1%AI IDX4,821+1.9%
PKT
SEEDRefresh Models Deals Regulatory Sources

ifeval

100 models tracked

IFEval — Same metric as 'IFEval strict-prompt', matching median (84.3) - same axis, diff formatting.

#ModelVendorBest scoreRunsLast seen
1Gemma 4 26B A4BGoogle96.412026-05-02
2Qwen3.5 27BAlibaba9512026-08-23
3Qwen3.7 Plus PreviewAlibaba94.612026-08-23
4Qwen3.6 PlusAlibaba94.312026-08-23
5Qwen3.7 MaxAlibaba94.312026-08-23
6o3-miniOpenAI93.912026-08-23
7Qwen3.5 122B A10BAlibaba93.412026-08-23
8Claude 3.7 SonnetAnthropic93.212026-08-23
9Qwen3.5 397B A17BAlibaba92.612026-08-23
10Llama 3.3 70B InstructMeta92.122026-08-23
11Nova Pro (Non-Reasoning)Amazon92.112026-08-23
12Qwen3.5 35B A3BAlibaba91.912026-08-23
13LFM2.5-8B-A1BLiquid AI91.812026-08-09
14Qwen3.5 9BAlibaba91.512026-08-23
15Gemma 4 26B A4B ITGoogle91.412026-08-09
16Qwen3 30B A3BAlibaba90.822026-08-09
17Gemma 3 27BGoogle90.422026-08-23
18NVIDIA Nemotron Nano 9B V2NVIDIA90.312026-08-23
19Gemma 3 4BGoogle90.222026-08-23
20Claude 3.5 SonnetAnthropic90.1122026-06-12
21Qwen3.5 4BAlibaba89.822026-08-23
22Kimi K2 InstructMoonshot89.842026-08-23
23Nova Lite (Non-Reasoning)Amazon89.712026-08-23
24Llama 3.1 Nemotron Ultra 253B V1NVIDIA89.512026-08-23
25Gemini 1.5 ProGoogle89.412026-06-12
26MiniMax Text 01MiniMax89.112026-06-12
27Qwen3 Next 80B A3BAlibaba88.912026-08-23
28Gemma 3 12BGoogle88.912026-08-23
29Qwen3 235B A22B Instruct 2507Alibaba88.712026-08-23
30Llama 3.1 Instruct 405BMeta88.642026-08-23
31lfm-2.5-1.2b-thinking:freeLiquid AI88.412026-08-09
32Gemini 2.0 Flash ExpGoogle88.412026-06-12
33Qwen3 32BAlibaba88.412026-06-15
34GPT-4.5 PreviewOpenAI88.212026-08-23
35Qwen3 VL 235B A22B ReasoningAlibaba88.212026-08-23
36Qwen3 VL 235B A22B InstructAlibaba87.812026-08-23
37Qwen3 VL 32B ReasoningAlibaba87.812026-08-23
38Gemma 4 E4BGoogle87.712026-08-09
39Claude Sonnet 4Anthropic87.622026-06-15
40Qwen3 Next 80B A3B InstructAlibaba87.612026-08-23
41Llama 3.1 70B InstructMeta87.532026-08-23
42Claude 4 OpusAnthropic87.422026-06-15
43GPT-4.1OpenAI87.412026-08-23
44DeepSeek-V3DeepSeek87.3102026-08-23
45Nova Micro (Non-Reasoning)Amazon87.212026-08-23
46Qwen2.5 Instruct 72BAlibaba87.232026-08-23
47gpt-oss-20bOpenAI86.712026-08-09
48Qwen3 VL 30B A3B InstructAlibaba85.812026-08-23
49Seed Oss 36B InstructByteDance85.812026-06-15
50Hunyuan Large Inst.Tencent8512026-05-31
51Phi 4 Reasoning PlusMicrosoft84.912026-08-23
52Sarvam 105BSarvam AI84.812026-08-23
53OpenAI o1-miniOpenAI84.8102026-06-05
54Qwen3 VL 32B InstructAlibaba84.712026-08-23
55GPT-4oOpenAI84.3132026-08-23
56GPT-4.1 miniOpenAI84.112026-08-23
57QwQ 32B PreviewAlibaba83.962026-08-23
58Qwen3 VL 8B InstructAlibaba83.712026-08-23
59DeepSeek-R1DeepSeek83.362026-06-04
60Qwen3 235B A22BAlibaba83.222026-06-15
61Qwen3 VL Thinking (8B)Alibaba83.212026-08-23
62Gemma 4 E2BGoogle82.912026-08-09
63Qwen3 VL 4B (Reasoning)Alibaba82.612026-08-23
64Qwen3 VL 4B InstructAlibaba82.312026-08-23
65LFM2.5-VL-3BLiquid AI82.322026-08-23
66Granite 4.0 H TinyIBM82.212026-08-09
67Qwen3 VL 30B A3B ReasoningAlibaba81.712026-08-23
68DeepSeek-V2.5DeepSeek80.612026-05-03
69Llama 3.1 8B InstructMeta80.422026-08-23
70Gemma 3 1BGoogle80.212026-08-23
71Granite 4.0 H 1BIBM80.112026-08-09
72Granite 4.0 1BIBM79.622026-08-09
73LFM2 2.6BLiquid AI79.612026-08-09
74Llama 3.1 Nemotron Nano 8B V1NVIDIA79.312026-08-23
75Qwen3.5 2BAlibaba78.622026-08-23
76R1-Distill-Qwen-14BAlibaba78.352026-06-05
77Llama 3.2 3B InstructMeta77.422026-08-23
78LFM2.5-350MLiquid AI7722026-08-09
79North-Micro-Vision-InstructCohere74.912026-08-23
80LFM2 1.2BLiquid AI74.912026-08-09
81Granite 3.3 8B InstructIBM74.822026-08-23
82GPT-4.1 nanoOpenAI74.512026-08-23
83Granite 3.2 8B InstructIBM74.312026-06-11
84Qwen3 1.7BAlibaba7422026-08-09
85Qwen3 1.7B (instruct)Alibaba73.722026-08-09
86LFM2-700MLiquid AI72.212026-08-09
87LFM2.5-230MLiquid AI71.712026-08-09
88Qwen3.5 0.8BAlibaba71.232026-08-23
89Granite 3.3 2B InstructIBM65.812026-06-11
90LFM2-350MLiquid AI65.132026-08-09
91Qwen3 0.6BAlibaba64.212026-08-09
92Granite 3.1 2B InstructIBM63.612026-06-11
93Gemma 3 1B ITGoogle63.552026-08-09
94Phi 4Microsoft6312026-08-23
95Granite 3.2 2B InstructIBM61.512026-06-11
96LFM2.5-VL-450M-ExtractLiquid AI61.212026-08-09
97MiMo 7B RLXiaomi6152026-06-05
98R1-Distill-Qwen-7BAlibaba60.552026-06-05
99Qwen3.5 0.8B (Instruct)Alibaba59.922026-08-09
100DeepSeek-V2DeepSeek57.712026-05-03

Best tracked score per model (default configuration; source-attributed and verification-tiered). Open a model for its full benchmark surface, provenance and pricing.