MicroEvals

Claude Opus 5 (Adaptive Reasoning, Max Effort)

Anthropic

GPT-5.6 Sol (max)

OpenAI

Qwen3.8 Max

Alibaba

Claude Opus 4.8 (Adaptive Reasoning, Max Effort)

Anthropic

Muse Spark 1.2 (xhigh)

Meta

GPT-5.6 Terra (max)

OpenAI

Grok 4.5 (high)

SpaceXAI

Claude Sonnet 5 (Adaptive Reasoning, Max Effort)

Anthropic

GLM-5.2 (max)

Z AI

GPT-5.6 Luna (max)

OpenAI

Gemini 3.6 Flash (high)

Google

Qwen3.7 Max

Alibaba

MiMo-V2.5-Pro

Xiaomi

Inkling (xhigh)

Thinking Machines

Nemotron 3 Ultra 550B A55B (Reasoning)

NVIDIA

Gemini 3.5 Flash-Lite

Google

Mistral Medium 3.5

Mistral

Claude 4.5 Haiku (Reasoning)

Anthropic

Gemma 4 31B (Reasoning)

Google

GPT-5.5 Pro (xhigh)

OpenAI

Claude 4.5 Haiku (Non-reasoning)

Anthropic

Claude Sonnet 4.6 (Adaptive Reasoning, Max Effort)

Anthropic

Claude Sonnet 4.6 (Non-reasoning, High Effort)

Anthropic

Claude Sonnet 4.6 (Non-reasoning, Low Effort)

Anthropic

Command A

Cohere

DeepSeek V4 Flash (Reasoning, Max Effort)

DeepSeek

DeepSeek V4 Pro (Reasoning, Max Effort)

DeepSeek

Devstral 2

Mistral

Gemini 3.1 Flash-Lite

Google

Gemini 3.5 Flash (high)

Google

Gemini 3.5 Flash (medium)

Google

Gemma 4 26B A4B (Reasoning)

Google

GLM 5V Turbo (Reasoning)

Z AI

GLM-5-Turbo

Z AI

GLM-5.1 (Reasoning)

Z AI

GPT-5.3 Codex (xhigh)

OpenAI

GPT-5.4 mini (xhigh)

OpenAI

GPT-5.4 nano (xhigh)

OpenAI

GPT-5.5 (xhigh)

OpenAI

gpt-oss-20b (high)

OpenAI

Granite 4.1 8B

IBM

Grok 4.3 (high)

SpaceXAI

Grok 4.3 (low)

SpaceXAI

Grok Build 0.1 0616

SpaceXAI

Hy3

Tencent

INTELLECT-3

Prime Intellect

KAT Coder Pro V2

KwaiKAT

KAT-Coder-Pro V1

KwaiKAT

Kimi K2.6

Kimi

Kimi K2.7 Code

Kimi

Ling 2.6 Flash

InclusionAI

Ling-2.6-1T

InclusionAI

Llama 4 Scout

Meta

Llama Nemotron Super 49B v1.5 (Reasoning)

NVIDIA

LongCat 2.0

LongCat

Mercury 2

Inception

MiMo-V2-Flash (Feb 2026)

Xiaomi

MiMo-V2-Flash (Non-reasoning)

Xiaomi

MiMo-V2.5

Xiaomi

MiniMax-M2.7

MiniMax

Mistral Large 3

Mistral

Mistral Small 4 (Reasoning)

Mistral

Muse Spark 1.1 (xhigh)

Meta

Nex-N2-Pro

Nex AGI

North Mini Code

Cohere

Nova 2.0 Lite (low)

Amazon

Nova 2.0 Lite (medium)

Amazon

Nova 2.0 Lite (Non-reasoning)

Amazon

Nova Premier

Amazon

NVIDIA Nemotron 3 Nano 30B A3B (Reasoning)

NVIDIA

Qwen3 Coder Next

Alibaba

Qwen3 Next 80B A3B (Reasoning)

Alibaba

Qwen3.5 122B A10B (Reasoning)

Alibaba

Qwen3.5 397B A17B (Non-reasoning)

Alibaba

Qwen3.5 397B A17B (Reasoning)

Alibaba

Qwen3.6 27B (Reasoning)

Alibaba

Qwen3.6 Plus

Alibaba

Qwen3.7 Plus

Alibaba

Ring-2.6-1T

InclusionAI

Step 3.7 Flash

StepFun

Trinity Large Thinking

Arcee AI