Code & Software Engineering

Artificial Analysis public leaderboard

CritPt

Critical-points programming evaluation published by Artificial Analysis.

Published source

Metric

Accuracy

Results shown

520

Publisher

Artificial Analysis

Snapshot

Fetched 2026-09-08T22:57:37.545Z

520 of 520 models

Higher is better

GPT-5.6 Sol (max)

GPT-6 Astra (max)

GPT-6 Astra (xhigh)

Claude Fable 5.1 (xhigh with fallback)

GPT-5.5 Pro (xhigh)

Claude Fable 5.1 (high with fallback)

GPT-5.4 Pro (xhigh)

GPT-5.6 Terra (max)

Claude Fable 5.1 (max with fallback)

Claude Fable 5.1 (medium with fallback)

Claude Opus 5 (max)

GPT-6 Astra (medium)

GPT-6 Astra (high)

GPT-5.6 Sol (xhigh)

Claude Fable 5 (with fallback)

Claude Opus 5 (high)

Claude Fable 5.1 (low with fallback)

Claude Opus 5 (xhigh)

GPT-5.5 (xhigh)

GPT-5.6 Terra (xhigh)

Claude Opus 5 (medium)

GPT-6 Astra (low)

Muse Spark 1.3 (xhigh)

GPT-5.6 Sol (high)

Gemini 3 Deep Think

GPT-5.5 (high)

Muse Spark 1.3 (max)

GPT-5.4 (xhigh)

Kimi K3 (max)

Claude Opus 5 (low)

GPT-5.6 Sol (medium)

GPT-5.6 Terra (high)

Claude Opus 4.8 (max)

GLM-5.2 (max)

GPT-5.6 Luna (max)

GPT-5.6 Luna (xhigh)

Qwen3.8 Max

Qwen3.8 2.4T A95B

GPT-6 Astra (Non-reasoning)

Grok 4.6 (xhigh)

GLM-5.3 (max)

GPT-5.5 (medium)

Gemini 3.8 Flash (high)

DeepSeek V4 Pro 0813 (max)

Muse Spark 1.2 (xhigh)

Grok 4.6 (medium)

Gemini 3.1 Pro Preview

GPT-5.6 Terra (medium)

Grok 4.6 (high)

Claude Sonnet 5 (max)

GPT-5.3 Codex (xhigh)

GPT-5.6 Luna (high)

DeepSeek V4 Flash 0731 (max)

Agnes 2.5 Pro Beta

GLM-5.3-Flash

Grok 4.5 (high)

Muse Spark 1.1 (xhigh)

GPT-5.6 Sol (low)

Gemini 3.7 Flash (high)

Qwen3.7 Max

Gemini 3.5 Flash

DeepSeek V4 Pro (max)

Claude Opus 4.6 (max)

Gemini 3.8 Flash (medium)

Claude Opus 4.7 (max)

GPT-5.2 (xhigh)

Muse Spark

Qwen3.8-Flash-Next

Gemini 3.5 Flash (medium)

DeepSeek V4 Flash Vision (max)

Agnes 2.5 Pro Alpha

Gemini 3.6 Flash

DeepSeek V4 Pro (high)

Kimi K2.7 Code

GPT-5.4 mini (xhigh)

GPT-5.6 Terra (low)

Gemini 3.7 Flash (medium)

Quasar 438B (max)

GPT-5.4 nano (xhigh)

Grok Build 0.1 0616

Qwen3.7 Plus

Gemini 3 Pro Preview (high)

A.X-K2

GPT-5.2 Codex (xhigh)

Nex-N2-Pro

Gemini 3 Flash

Claude Sonnet 5 (medium)

Inkling Small

Kimi K2.6

Grok 4.3 (high)

GPT-5.5 (low)

GPT-5.2 (medium)

DeepSeek V3.2 Speciale

GPT-5.4 (low)

DeepSeek V4 Flash (max)

Motif 3

Grok 4.20 0309 v2

Grok 4.20 0309

Motif 3 (Beta)

GPT-5.1 Codex (high)

GPT-5 (high)

Solar Open2 250B

Grok 4.6 (low)

Gemini 3.7 Flash (low)

Inkling

Solar Pro 4

Qwen3.8 27B (xhigh)

Claude Opus 4.7 (Non-reasoning, high)

GPT-5 Codex (high)

GPT-5.6 Sol (Non-reasoning)

GPT-5.4 nano

GPT-5.1 (high)

GPT-5.6 Luna (medium)

Grok 4.3 (medium)

Hy3

Apodex 1.1

Claude Sonnet 5 (low)

Claude Opus 4.5

GLM-5.1

Hy3-preview

K2 Horizon 375B A23B

MiMo-V2-Flash

MiMo-V2.5-Pro

Gemini 3.8 Flash (low)

MiMo-V2.5

MiniMax-M3

Ring-2.6-1T

Qwen3.6 Max Preview

DeepSeek V4 Flash (high)

Kimi K3 (low)

Nemotron 3 Ultra

Nemotron 3 Super

Kimi K2.5

Claude Sonnet 4.6 (max)

GLM-5.2 (Non-reasoning)

MiMo-V2-Flash (Feb 2026)

Grok 4.1 Fast

GPT-5.4 mini (medium)

Grok 4 Fast

DeepSeek V3.2

Qwen3.6 Plus

Claude Opus 4.6 (Non-reasoning, high)

GPT-5.6 Luna (low)

Gemini 2.5 Pro

Muse Glimmer (high)

LongCat 2.0

Kimi K2 Thinking

GPT-5.5 Instant (May 2026)

Step 3.5 Flash

Step 3.5 Flash 2603

Step 3.7 Flash

DeepSeek V3.1

GLM-5

Grok 4

GPT-5.6 Terra (Non-reasoning)

DeepSeek V3.1 Terminus

Qwen3 Max Thinking

Ling 3.0 Flash

GLM-4.7

Qwen3.5 397B A17B

Gemini 3.5 Flash (minimal)

DeepSeek V3.2 Exp (Non-reasoning)

Kimi K2.6 (Non-reasoning)

gpt-oss-20b (high)

Gemini 2.5 Flash (Non-reasoning)

GPT-5.5 (Non-reasoning)

Gemini 3 Flash (Non-reasoning)

ERNIE 5.0 Thinking Preview

DeepSeek R1 0528

DeepSeek V3.2 Exp

GPT-5 mini (medium)

Gemma 4 31B

MiniMax-M2.5

Gemini 2.5 Flash

MiMo-V2.5-Pro (Non-reasoning)

Gemini 3.1 Flash-Lite

GLM-4.6

GPT-5 (low)

Qwen3.6 27B

Claude 4.5 Sonnet

MiMo-V2-Omni

Apriel-v1.5-15B-Thinker

Claude 4 Sonnet (Non-reasoning)

Claude Sonnet 5 (Non-reasoning)

gpt-oss-120b (high)

K-

K-EXAONE

Qwen3.5 122B A10B (Non-reasoning)

Claude 3.7 Sonnet

K-

K-EXAONE 2.0

MiMo-V2-Omni-0327

Claude Sonnet 4.6 (Non-reasoning, high)

Qwen3.5 397B A17B (Non-reasoning)

HyperNova 60B 2605 (high)

Qwen3.6 27B (Non-reasoning)

Qwen3.5 35B A3B

Qwen3 Max (Preview)

DeepSeek V3.2 (Non-reasoning)

DeepSeek V4 Pro (Non-reasoning)

Nemotron 3 Nano

Trinity Large Thinking

Claude Sonnet 4.6 (Non-reasoning, low)

MiniMax-M2

Qwen3.5 27B

Mercury 2

DeepSeek R1 (Jan)

Ling-1T

Qwen3.5 9B (Non-reasoning)

Qwen3.5 122B A10B

GLM 5V Turbo

GPT-5.4 (Non-reasoning)

MiniMax-M2.7

GPT-5.2 (Non-reasoning)

o4-mini (high)

Nemotron Cascade 2 30B A3B

Ring-1T

Kimi K2.5 (Non-reasoning)

Gemma 4 E4B

Qwen3.5 35B A3B (Non-reasoning)

Grok 4.3 (low)

Grok 3 mini Reasoning (high)

Qwen3.5 Omni Plus

o3-mini (high)

Granite 4.2 30B

Mistral Small 4 (Non-reasoning)

GLM-5-Turbo

North Mini Code

MiniMax-M2.1

GLM-4.7-Flash

Qwen3.5 9B

Ling-2.6-1T

Command A+

Qwen3.8 27B

INTELLECT-3

Mistral Small 4

Claude Opus 4.5 (Non-reasoning)

Doubao Seed Code

EXAONE 4.5 33B

Qwen3.5 27B (Non-reasoning)

Gemma 4 E4B (Non-reasoning)

MiMo-V2-Pro

Tri-21B-Think

Qwen3 30B A3B 2507

Nova 2.0 Lite (high)

MiniCPM5-2B

Grok 4.20 0309 v2 (Non-reasoning)

Magistral Medium 1

Magistral Small 1.2

Sarvam 30B (high)

Hermes 4 405B

Magistral Medium 1.2

Qwen3.6 35B A3B

Apriel-v1.6-15B-Thinker

Claude 4 Sonnet

DeepSeek V4 Flash (Non-reasoning)

Granite 4.2 8B

Qwen3 32B

Hy3-preview (Non-reasoning)

G9v3-39A5B

DiffusionGemma 26B A4B

Gemini 2.5 Flash (Sep)

Falcon-H1R-7B

GPT-5.6 Luna (Non-reasoning)

Qwen3 VL 8B (Reasoning)

Ring-flash-2.0

GLM-4.5V (Non-reasoning)

JT-35B-Flash

Nova 2.0 Omni (medium)

Gemma 4 12B (Non-reasoning)

Claude 3.5 Haiku

Gemma 3 270M

Mistral Medium 3.1

GPT-5 nano (minimal)

Qwen3 Coder 480B

Gemini 3.5 Flash-Lite

Qwen3.5 2B (Non-reasoning)

Devstral 2

Qwen3 Omni 30B A3B

Granite 4.2 3B

Nova 2.0 Pro Preview (medium)

Qwen3 0.6B (Non-reasoning)

LFM2 1.2B

Magistral Small 1

gpt-oss-20b (low)

Llama 3.3 Nemotron Super 49B

GLM-4.5

Gemini 2.5 Flash-Lite (Non-reasoning)

Nova 2.0 Omni (Non-reasoning)

Granite 4.0 Micro

Claude 3 Haiku

Mistral 7B

Gemma 3 4B

Hermes 4 70B (Non-reasoning)

Nemotron 3 Nano (Non-reasoning)

Grok 3

Mistral Small 3.1

Qwen3 Next 80B A3B

Llama Nemotron Super 49B v1.5 (Non-reasoning)

GPT-5 mini (high)

Nemotron 3.5 Lightning

Qwen3 4B 2507

Qwen3 1.7B (Non-reasoning)

Gemma 3 27B

Granite 3.3 8B

Grok 4 Fast (Non-reasoning)

Gemma 3 12B

NVIDIA Nemotron Nano 9B V2 (Non-reasoning)

EXAONE 4.0 32B (Non-reasoning)

G9v3-3B

GLM-4.5V

Qwen3.5 4B (Non-reasoning)

Qwen3 235B 2507 (Non-reasoning)

Olmo 3 7B Think

HyperCLOVA X SEED Think (32B)

Nova Micro

Sarvam M

Olmo 3.1 32B Think

GPT-4.1

Command A

LFM2.5-VL-1.6B

Qwen3 VL 8B

JT-MINI

Ling-mini-2.0

Qwen3 30B

Molmo2-8B

Qwen3.5 0.8B (Non-reasoning)

GLM-4.6V (Non-reasoning)

MiniCPM-V 4.6 1.3B

Qwen3 235B (Non-reasoning)

Mistral Small 3.2

DeepSeek V3 (Dec)

Kimi K2

EXAONE 4.0 32B

Solar Pro 2 (Non-reasoning)

Qwen3 14B

Sarvam 105B (high)

Llama 3.1 405B

Llama 3.1 70B

LFM2.5-1.2B-Instruct

Mistral Large 3

Apertus 70B Instruct

Grok 4.1 Fast (Non-reasoning)

DeepSeek R1 Distill Llama 70B

Qwen3 0.6B

Mistral Large 2 (Nov)

Qwen3 VL 30B A3B

Grok 4.20 0309 (Non-reasoning)

Nova Pro

Granite 4.0 350M

Qwen3 1.7B

Solar Open 100B

Mistral Medium 3

LFM2.5-1.2B-Thinking

K2 Think V2

Nova Lite

Seed-OSS-36B-Instruct

GLM-4.5-Air

Qwen3.5 2B

Granite 4.0 H Small

GPT-5 (medium)

Llama 3.2 11B (Vision)

DeepSeek R1 0528 Qwen3 8B

LongCat Flash Lite

Tri-21B-think Preview

Qwen3.5 4B

Kimi K2 0905

Qwen3.8 27B (medium)

Motif-2-12.7B

Qwen3.6 35B A3B (Non-reasoning)

Ministral 3 3B

LFM2 8B A1B

Hermes 4 70B

Qwen3 VL 32B

Gemma 4 26B A4B

NVIDIA Nemotron Nano 12B v2 VL

Qwen3.5 Omni Flash

Nova 2.0 Lite (low)

Gemma 4 26B A4B (Non-reasoning)

Ministral 3 14B

Gemini 2.5 Flash-Lite (Sep) (Non-reasoning)

GPT-4.1 nano

Llama 3.1 Nemotron 70B

Llama 3.1 8B

LFM2 2.6B

Gemma 4 E2B (Non-reasoning)

DeepSeek V3 0324

Nova 2.0 Lite (Non-reasoning)

MiniCPM5-1B

Jamba 1.7 Large

Qwen3 Max

Nanbeige4.1-3B

Qwen3.8 27B (low)

Ling 3.0 Tiny

Qwen3 30B A3B 2507 (Non-reasoning)

Celeris-1

Llama 3.2 1B

Tiny Aya Global

GLM-4.7 (Non-reasoning)

Exaone 4.0 1.2B (Non-reasoning)

Llama 3 8B

MiMo-V2-Flash (Non-reasoning)

Granite 4.1 8B

Gemini 2.5 Flash-Lite (Sep)

Gemini 2.5 Flash (Sep) (Non-reasoning)

Ling-flash-2.0

Apertus 8B Instruct

GPT-4o (Aug)

Nemotron 3 Nano Omni 30B A3B

GPT-5 nano (medium)

Olmo 3 7B

JT-4.1 Flash 236B A21B

Grok 4.3 (Non-reasoning)

Claude 4.5 Sonnet (Non-reasoning)

Granite 4.1 3B

Ling 2.6 Flash

Llama 4 Maverick

GLM-5.1 (Non-reasoning)

GLM-4.6 (Non-reasoning)

Olmo 3.1 32B Instruct

Ministral 3 8B

Llama 3.3 70B

MiniMax M1 80k

K-

K-EXAONE (Non-reasoning)

Qwen3 8B

Devstral Small

Nemotron 3 Nano 4B

GPT-4.1 mini

Phi-4 Mini

Grok Code Fast 1

Nova 2.0 Pro Preview (Non-reasoning)

Granite 4.0 1B

K2-V2 (high)

Claude 4.5 Haiku

Granite 4.0 H 350M

Qwen3.5 0.8B

Gemma 3n E4B

Qwen3 VL 235B A22B (Reasoning)

Gemma 3n E2B

Llama 3 70B

NVIDIA Nemotron Nano 12B v2 VL (Non-reasoning)

Devstral Medium

Step3 VL 10B

Llama 4 Scout

GPT-5.4 mini (Non-reasoning)

ERNIE 4.5 300B A47B

Qwen3 4B 2507 (Non-reasoning)

Gemma 4 E2B

Qwen3 8B (Non-reasoning)

Gemini 3 Pro Preview (low)

Nova 2.0 Omni (low)

Jamba 1.7 Mini

Qwen2.5 72B

Solar Pro 3

Qwen3 Omni 30B A3B (Reasoning)

Qwen3 235B

GPT-5 mini (minimal)

Gemini 2.0 Flash

GPT-4o (Nov)

GPT-5.4 nano (Non-reasoning)

Claude 4.5 Haiku (Non-reasoning)

GPT-5 (minimal)

GPT-5.5 Instant (June 2026)

Llama 3.3 Nemotron Super 49B (Non-reasoning)

GLM-4.7-Flash (Non-reasoning)

Olmo 3 32B Think

Qwen3 Next 80B A3B (Reasoning)

gpt-oss-120b (low)

Qwen3 Max Thinking (Preview)

Devstral Small (May)

Claude 4.1 Opus

Qwen3 VL 30B A3B (Reasoning)

Devstral Small 2

Llama Nemotron Ultra

Gemma 4 31B (Non-reasoning)

GPT-5.1 (Non-reasoning)

Gemma 3 1B

GLM-4.6V

MiniCPM5-1B (Non-reasoning)

Qwen3 VL 32B (Reasoning)

Hermes 4 405B (Non-reasoning)

Granite 4.1 30B

Qwen3 VL 235B A22B

Exaone 4.0 1.2B

Claude 3.7 Sonnet (Non-reasoning)

Qwen3 Coder 30B A3B

K2-V2 (low)

Granite 4.0 H 1B

Reka Flash 3

Mistral Medium 3.5

K2-V2 (medium)

Mi:dm K 2.5 Pro

DeepSeek V3.1 Terminus (Non-reasoning)

Mi:dm K 2.5 Pro Preview

GPT-5 nano (high)

LFM2.5-2.6B

Llama Nemotron Super 49B v1.5

LFM2.5-8B-A1B

Nova Premier

Cogito v2.1

Solar Pro 2

Qwen3 14B (Non-reasoning)

Phi-4

GLM-5 (Non-reasoning)

NVIDIA Nemotron Nano 9B V2

Qwen3 30B (Non-reasoning)

Nova 2.0 Pro Preview (low)

Gemini 2.5 Flash-Lite

Qwen3 VL 4B

Qwen3 235B A22B 2507

Jamba Reasoning 3B

Qwen3 VL 4B (Reasoning)

KAT-Coder-Pro V1

DeepSeek V3.1 (Non-reasoning)

LFM2 24B A2B

Nova 2.0 Lite (medium)

KAT-Coder-Pro V2

Qwen3 Coder Next

GPT-5.1 Codex mini (high)

Gemma 4 12B

List bars visualize relative performance. Plot bars use published 0–100 scores, shrink to a 1.5rem minimum, then scroll horizontally.

Scores are published snapshots and are only comparable within the same benchmark, version, metric, and evaluation configuration.