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

livecodebench_medium

19 models tracked

LiveCodeBench, Medium difficulty subset — Difficulty-tier subset, never merge with overall/easy/hard scores.

#ModelVendorBest scoreRunsLast seen
1o4-miniOpenAI92.232026-05-03
2Gemini 2.5 Pro Preview 06.05 (32k think)Google92.212026-05-30
3DeepSeek-R1DeepSeek90.912026-05-03
4Gemini 2.5 ProGoogle90.622026-05-03
5o3OpenAI89.812026-05-03
6Qwen3 235B A22BAlibaba88.812026-05-03
7EXAONE 4.0 32BLG AI88.312026-05-03
8OpenReasoning-Nemotron-32BNVIDIA87.512026-05-03
9o3-miniOpenAI87.532026-06-18
10Grok 3 Mini ReasoningSpaceXAI85.912026-05-03
11OpenCodeReasoning-Nemotron-1.1-32BNVIDIA85.712026-05-03
12Gemini 2.5 FlashGoogle82.532026-06-20
13Claude 4 OpusAnthropic80.422026-05-29
14Claude Sonnet 4Anthropic7622026-05-15
15DeepSeek-V3DeepSeek53.512026-05-03
16GPT-4oOpenAI32.112026-05-03
17GPT-4 TurboOpenAI30.712026-05-03
18GPT-4o miniOpenAI25.212026-05-03
19Claude 3 HaikuAnthropic912026-05-03

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