LiveCodeBench benchmark
144 AI models ranked on LiveCodeBench. Each row shows the model’s score next to its cheapest API price per 1M tokens where it has one, so you can weigh quality against cost.
Top model today
Gemini 3 Pro (Google) leads at 92%, from $2.00 per 1M input via Replicate.
Data via arXiv:2403.07974 →Models ranked
144
on this benchmark
Top score
92%
current leader
Type
Single eval
benchmark
Updated
Oct 14, 2026
benchmark scores
Cost vs LiveCodeBench
118 priced models = reasoning model (extended thinking)
Each labelled name links to that model’s page. Curated to the cost-efficiency frontier, top scorers and cheapest so labels stay readable; the full field is in the leaderboard table below (and via “select all”). Reasoning models (extended “thinking” before answering) carry a ring around the dot.
Models ranked on LiveCodeBench
highest score first · 144 modelsMaker
| # | ||||||||||||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 1 | Gemini 3 Pro |  Google | 92% | $2.00 via Replicate | $12.00 via Replicate | |||||||||||||||||||||
| ||||||||||||||||||||||||||
| 2 | Gemini 3 Flash | Google | 91%reasoning: true | $0.50 Routed quote | $3.00 Routed quote | |||||||||||||||||||||
| ||||||||||||||||||||||||||
| 3 | GLM 4.7 |  Zhipu | 89% | $0.40 via DeepInfra | $1.75 via DeepInfra | |||||||||||||||||||||
| ||||||||||||||||||||||||||
| 4 | GPT-5.2 |  OpenAI | 89%medium | $1.75 via OpenAI | $14.00 via OpenAI | |||||||||||||||||||||
| ||||||||||||||||||||||||||
| 5 | gpt-oss-120b | OpenAI | 88% | $0.03 via Wandb | $0.17 via DeepInfra | |||||||||||||||||||||
| ||||||||||||||||||||||||||
| 6 | Claude Opus 4.5 |  Anthropic | 87%reasoning: true | $5.00 via Anthropic | $25.00 via Anthropic | |||||||||||||||||||||
| ||||||||||||||||||||||||||
| 7 | GPT-5.1 | OpenAI | 87% | $1.25 via Databricks | $10.00 via Databricks | |||||||||||||||||||||
| ||||||||||||||||||||||||||
| 8 | Mimo V2 Flash |  Xiaomi | 87%reasoning: true | $0.10 Routed quote | $0.30 Routed quote | |||||||||||||||||||||
| ||||||||||||||||||||||||||
| 9 | DeepSeek V3.2 |  DeepSeek | 86%reasoning: true | $0.259 Routed quote | $0.38 via DeepInfra | |||||||||||||||||||||
| ||||||||||||||||||||||||||
| 10 | o4 Mini | OpenAI | 86% | $1.00 via Replicate | $4.00 via Replicate | |||||||||||||||||||||
| 11 | Kimi K2 Thinking |  Moonshot | 85% | $0.60 via Moonshot | $1.20 via Gmi | |||||||||||||||||||||
| 12 | GPT-5.1-Codex | OpenAI | 85% | $1.25 Routed quote | $10.00 Routed quote | |||||||||||||||||||||
| 13 | GPT-5 | OpenAI | 85% | $1.25 via Databricks | $10.00 via Databricks | |||||||||||||||||||||
| ||||||||||||||||||||||||||
| 14 | GPT 5 Codex | OpenAI | 84% | $1.25 Routed quote | $10.00 Routed quote | |||||||||||||||||||||
| 15 | GPT-5 Mini | OpenAI | 84% | $0.25 via Databricks | $1.20 via Snowflake | |||||||||||||||||||||
| ||||||||||||||||||||||||||
| 16 | GPT-5.1-Codex-Mini | OpenAI | 84% | $0.25 via Databricks | $2.00 via Databricks | |||||||||||||||||||||
| 17 | Grok 4 Fast Reasoning |  xAI | 83% | $0.20 via Azure | $0.50 via Azure | |||||||||||||||||||||
| 18 | MiniMax M2 |  MiniMax | 83% | $0.255 Routed quote | $1.02 Routed quote | |||||||||||||||||||||
| 19 | Grok 4 | xAI | 82% | $1.25 via xAI | $2.50 via xAI | |||||||||||||||||||||
| 20 | MiniMax M2.1 | MiniMax | 81% | $0.30 via Minimax | $1.20 via Minimax | |||||||||||||||||||||
| 21 | o3 | OpenAI | 81% | $2.00 via OpenAI | $8.00 via OpenAI | |||||||||||||||||||||
| 22 | Apriel-v1.6-15B-Thinker | Servicenow | 81% | n/a | n/a | |||||||||||||||||||||
| 23 | Gemini 2.5 Pro | Google | 80% | $1.25 via Databricks | $10.00 via Databricks | |||||||||||||||||||||
| 24 | DeepSeek V3.1 Terminus | DeepSeek | 80%reasoning: true | $0.27 via DeepInfra | $1.00 via DeepInfra | |||||||||||||||||||||
| ||||||||||||||||||||||||||
| 25 | GPT-5 Nano | OpenAI | 79% | $0.05 via Databricks | $0.40 via Databricks | |||||||||||||||||||||
| ||||||||||||||||||||||||||
| 26 | DeepSeek V3.2 Exp (0925) (Reasoning) | DeepSeek | 79% | n/a | n/a | |||||||||||||||||||||
| 27 | Qwen3 235B A22b Instruct 2507 |  Alibaba | 79%reasoning: true | $0.09 via DeepInfra | $0.10 via Wandb | |||||||||||||||||||||
| ||||||||||||||||||||||||||
| 28 | DeepSeek V3.1 | DeepSeek | 78%reasoning: true | $0.25 via DeepInfra | $0.95 via DeepInfra | |||||||||||||||||||||
| ||||||||||||||||||||||||||
| 29 | Qwen3 Next 80B A3b | Alibaba | 78%reasoning: true | $0.15 via Amazon Bedrock | $1.20 via Amazon Bedrock | |||||||||||||||||||||
| 30 | gpt-oss-20b | OpenAI | 78% | $0.0145 via Darkbloom | $0.07 via Darkbloom | |||||||||||||||||||||
| ||||||||||||||||||||||||||
| 31 | R1 0528 | DeepSeek | 77% | $0.20 via Lambda AI | $0.25 via Hyperbolic | |||||||||||||||||||||
| 32 | Gemini 2.5 Pro (May) | Google | 77% | n/a | n/a | |||||||||||||||||||||
| 33 | Qwen3 Max | Alibaba | 77% | $0.78 Routed quote | $3.90 Routed quote | |||||||||||||||||||||
| 34 | Seed-OSS-36B-Instruct | ByteDance Seed | 77% | n/a | n/a | |||||||||||||||||||||
| 35 | Nvidia Nemotron Nano 3 30B |  NVIDIA | 74%reasoning: true | $0.06 via Amazon Bedrock | $0.24 via Amazon Bedrock | |||||||||||||||||||||
| ||||||||||||||||||||||||||
| 36 | o3 Mini High | OpenAI | 73% | $1.10 Routed quote | $4.40 Routed quote | |||||||||||||||||||||
| 37 | Nova 2.0 Pro Preview |  Amazon | 73%medium | n/a | n/a | |||||||||||||||||||||
| ||||||||||||||||||||||||||
| 38 | Apriel-v1.5-15B-Thinker | Servicenow | 73% | n/a | n/a | |||||||||||||||||||||
| 39 | Nvidia Nemotron Nano 9B V2 | NVIDIA | 72%reasoning: true | $0.04 via DeepInfra | $0.16 via DeepInfra | |||||||||||||||||||||
| ||||||||||||||||||||||||||
| 40 | Magistral Small 2509 |  Mistral | 72% | $0.50 via Amazon Bedrock | $1.50 via Amazon Bedrock | |||||||||||||||||||||
| 41 | o3 Mini | OpenAI | 72% | $1.10 via OpenAI | $4.40 via OpenAI | |||||||||||||||||||||
| 42 | Claude 4.5 Sonnet | Anthropic | 71%reasoning: true | $3.00 via Replicate | $15.00 via Replicate | |||||||||||||||||||||
| ||||||||||||||||||||||||||
| 43 | MiniMax M1 80k | MiniMax | 71% | $0.10 via Fireworks AI | $0.10 via Fireworks AI | |||||||||||||||||||||
| 44 | Nova 2.0 Lite | Amazon | 71%reasoning: true | n/a | n/a | |||||||||||||||||||||
| ||||||||||||||||||||||||||
| 45 | Grok 3 Mini | xAI | 70%reasoning: true | $0.25 via Azure | $0.50 via OCI | |||||||||||||||||||||
| 46 | GLM 4.6 | Zhipu | 70%reasoning: true | $0.50 via DeepInfra | $2.00 via DeepInfra | |||||||||||||||||||||
| ||||||||||||||||||||||||||
| 47 | Gemini 2.5 Flash | Google | 70%reasoning: true | $0.15 via OCI | $0.60 via OCI | |||||||||||||||||||||
| ||||||||||||||||||||||||||
| 48 | Olmo 3.1 32B Think |  Allen AI | 70% | n/a | n/a | |||||||||||||||||||||
| 49 | Gemini 2.5 Flash Lite Preview 09 2025 | Google | 69%reasoning: true | $0.10 via Google | $0.40 via Google | |||||||||||||||||||||
| ||||||||||||||||||||||||||
| 50 | Cogito 671B V2 P1 | Other | 69%reasoning: true | $1.20 via Fireworks AI | $1.20 via Fireworks AI | |||||||||||||||||||||
1–50 of 268
Page 1 of 6
On-demand listed rates, OpenRouter routed quotes and Vercel reseller quotes. Enterprise commitments can be materially lower. Cost per task uses best-effort token usage. An OpenRouter routed quote is the price of whichever upstream provider OpenRouter prefers today, so it moves day to day.
Frequently asked questions
What is the LiveCodeBench benchmark?
A contamination-free coding benchmark that continuously collects new competitive-programming problems from LeetCode, AtCoder and Codeforces, tagging each with a release date so models are tested only on problems published after their training cutoff. It scores code generation, self-repair, execution and test-output prediction.
Which AI model scores highest on LiveCodeBench?
Gemini 3 Pro (Google) leads with 92%, from $2.00 per 1M input tokens from Replicate.
How many models are ranked on LiveCodeBench?
144 models carry a LiveCodeBench score. Scores come from Artificial Analysis; where a model has a listed API price it is drawn from LiteLLM and OpenRouter, and models with no current price are listed without one.
Other benchmarks
compare the same models on a different evalIntelligence Indexcomposite indexCoding Indexcomposite indexAgentic Indexcomposite indexGPQA DiamondleaderboardHumanity's Last ExamleaderboardMMLU-ProleaderboardMMMU-ProleaderboardSciCodeleaderboardTerminalBench HardleaderboardTerminalBench v2.1leaderboardτ²-benchleaderboardτ-bench BankingleaderboardAPEX AgentsleaderboardIT-Bench SREleaderboardGDPvalleaderboardCritPtleaderboardOmniscienceleaderboardIFBenchleaderboardLong-Context Reasoningcomposite indexSWE-bench VerifiedleaderboardSWE-bench ProleaderboardAIME 2026leaderboardARC-AGI-2leaderboardAA-Briefcaseleaderboard
Benchmark scores via Artificial Analysis · scores updated Oct 14, 2026 · Listed prices from LiteLLM, OpenRouter and Vercel · catalogue refreshed Oct 14, 2026 · 96 prices older, back to Jul 19, 2026
Every weekday
AI moves fast. Here's your debrief.
News, analysis, tools, and more.
For people who build with AI