Refresh Models —Deals —Regulatory —Sources —

Kimi K2 Instruct vs Llama 3.1 Instruct 405B

34 SHARED BENCHMARKS

Across 34 shared benchmarks, Kimi K2 Instruct scores higher on 31 and Llama 3.1 Instruct 405B on 2, with 1 level. The widest gap is AA Agentic Index, where Kimi K2 Instruct scores 37.7 against 6.3.

MOONSHOTVSMETA34 SHARED31–2 HEAD-TO-HEAD

BenchmarkKimi K2 InstructMARGINLlama 3.1 Instruct 405B

AA Agentic Index37.76.3

AA Intelligence248.5

AA-LCR53.724.7

AA-Omniscience-26.6-17.1

aider_polyglot605.8

AIME 202469.623.3

AIR-Bench 202474.158.6

anthropic_red_team99.396.5

Artificial Analysis Coding Index25.914.5

bbq94.994.5

GPQA Diamond7751.5

GSM8K97.396.8

harmbench97.462.7

HLE7.94.2

humaneval94.589

ifeval89.888.6

LiveCodeBench6130.1

math_500_em97.473.8

mmlu89.588.6

mmlu_redux92.786.2

MMLU-Pro82.573.4

OmniScience Accuracy25.423.2

OmniScience Non-Hallucination30.349

simple_safety_tests10098.8

SWE-bench Pro27.711.2

SWE-bench Verified69.224.5

Terminal-Bench Hard23.56.8

xstest98.295.9

τ²-Bench Telecom (AA run)73.419

Best tracked score per model per benchmark (default configuration; source-attributed). ↓ marks lower-is-better metrics. Open either model for its full surface, provenance and pricing.

Compare Kimi K2 Instruct withEVERY TRACKED PAIRING

▶Anthropic12 PAIRINGS

Claude Opus 4.8 Claude Opus 4.6 Claude Sonnet 4.5 Claude 3.5 Sonnet Claude Opus 4.5 Claude Fable 5 Claude Opus 5 Claude Opus 4.7 Claude Sonnet 4 Claude Sonnet 4.6 Claude Sonnet 5 Claude Opus 4

▶OpenAI11 PAIRINGS

GPT-5.5 GPT-4o GPT-5.6 Sol GPT-5.2 GPT-5.4 GPT-5 o3 GPT-5.1 o4-mini o1 GPT-4o mini

▶Google11 PAIRINGS

Gemini 3.1 Pro Gemini 3 Pro Gemma 4 26B A4B Gemini 1.5 Pro Gemma 4 31B Gemini 2.5 Pro Gemini 3.5 Flash Gemini 3 Flash Preview Gemini 3.6 Flash Gemma 4 E2B Gemini 2.5 Flash

▶Alibaba11 PAIRINGS

Qwen3.5 35B A3B Qwen3.5 397B A17B Qwen3 VL 4B (Reasoning)Qwen2.5 Instruct 72B Qwen3.5 27B Qwen3.6 Plus Qwen3.6 27B Qwen3.6 35B A3B Qwen3.7 Max Qwen3.5 122B A10B Qwen3.7 Plus Preview

▶DeepSeek5 PAIRINGS

DeepSeek-V3 DeepSeek-V4-Pro DeepSeek-V3.2 DeepSeek-V4-Flash DeepSeek-R1

▶Moonshot3 PAIRINGS

Kimi K2.5 Kimi K2.6 Kimi K3

▶Meta1 PAIRING

▶Z.ai2 PAIRINGS

GLM-5.1 GLM-5.2

▶MiniMax1 PAIRING

▶NVIDIA1 PAIRING

Nemotron 3 Super 120B A12B

Compare Llama 3.1 Instruct 405B withEVERY TRACKED PAIRING

▶Anthropic12 PAIRINGS

Claude Opus 4.8 Claude Opus 4.6 Claude Sonnet 4.5 Claude 3.5 Sonnet Claude Opus 4.5 Claude Fable 5 Claude Opus 5 Claude Opus 4.7 Claude Sonnet 4 Claude Sonnet 4.6 Claude Sonnet 5 Claude Opus 4

▶OpenAI11 PAIRINGS

GPT-5.5 GPT-4o GPT-5.6 Sol GPT-5.2 GPT-5.4 GPT-5 o3 GPT-5.1 o4-mini o1 GPT-4o mini

▶Google11 PAIRINGS

Gemini 3.1 Pro Gemini 3 Pro Gemma 4 26B A4B Gemini 1.5 Pro Gemma 4 31B Gemini 2.5 Pro Gemini 3.5 Flash Gemini 3 Flash Preview Gemini 3.6 Flash Gemma 4 E2B Gemini 2.5 Flash

▶Alibaba11 PAIRINGS

Qwen3.5 35B A3B Qwen3.5 397B A17B Qwen3 VL 4B (Reasoning)Qwen2.5 Instruct 72B Qwen3.5 27B Qwen3.6 Plus Qwen3.6 27B Qwen3.6 35B A3B Qwen3.7 Max Qwen3.5 122B A10B Qwen3.7 Plus Preview

▶DeepSeek5 PAIRINGS

DeepSeek-V3 DeepSeek-V4-Pro DeepSeek-V3.2 DeepSeek-V4-Flash DeepSeek-R1

▶Moonshot3 PAIRINGS

Kimi K2.5 Kimi K2.6 Kimi K3

▶Meta1 PAIRING

▶Z.ai2 PAIRINGS

GLM-5.1 GLM-5.2

▶MiniMax1 PAIRING

▶NVIDIA1 PAIRING

Nemotron 3 Super 120B A12B