BenchLeader

LiveCodeBench leaderboard

As of 15 Nov 2026, the top score on LiveCodeBench is 90.5% by Claude Fable 5.1 (Anthropic), ahead of Claude Fable 5 at 89.8%, across 140 model configurations with a published result (Vals AI, result dated 1 Sep 2026). LiveCodeBench collects competitive-programming problems published after each model's training cutoff and checks solutions by running hidden tests. LiveCodeBench counts toward the BenchLeader coding score.

Key facts (as of 15 Nov 2026)

  • Claude Fable 5.1 holds the top LiveCodeBench score at 90.5% (Vals AI, 1 Sep 2026).
  • Claude Fable 5 is second on LiveCodeBench at 89.8% (Vals AI, 1 Sep 2026).
  • LiveCodeBench: Competitive programming problems released after model cutoffs. Run by Vals AI (Vals AI).
  • 140 model configurations have a published LiveCodeBench result on BenchLeader (BenchLeader, 15 Nov 2026).
  • LiveCodeBench feeds the coding category of the BenchLeader Index (BenchLeader methodology).

Competitive programming problems released after model cutoffs. Run by Vals AI.

Published by
Vals AI
Category
Coding
Index weight
1.0
Models
140
Data as of
15 Nov 2026

Vals AI (vals.ai).

What the test looks like

LiveCodeBench collects competitive-programming problems published after each model's training cutoff and checks solutions by running hidden tests.

How it is scored

Percent of problems passing all tests; Vals AI runs a fixed recent window.

What to keep in mind

Only the window after a model's cutoff is contamination-free, and the window changes over time, so scores across dates are not strictly comparable.

140 of 140
#
1Claude Fable 5.1max90.5%66.7$0.2612026-09-01
2Claude Fable 5max89.8%65.1$0.4282026-09-01
3Gemini 3.8 Flashhigh89.5%59.4$0.0712026-09-01
4Claude Opus 5max89.0%65.0$0.1342026-09-01
5Gemini 3.7 Flashhigh88.7%62.1$0.0402026-09-01
6Gemini 3.1 Prohigh88.5%60.4$0.1012026-09-01
7Grok 4.6high88.2%60.6$0.0402026-09-01
8Gemini 3.6 Flashhigh88.1%61.0$0.0562026-09-01
9GPT-5.2-Codex88.0%57.6$0.1172026-09-01
10Qwen3.8 Maxmax87.8%58.7$0.0912026-09-01
11Claude Opus 4.8max87.8%61.1$0.3272026-09-01
12Gemini 3.5 Flashhigh87.6%62.5$0.0862026-09-01
13DeepSeek V4 Promax87.5%54.7$0.0642026-09-01
14Grok 4.5high87.3%56.8$0.0452026-09-01
15GPT-5.3-Codexxhigh87.3%62.9$0.0922026-09-01
16DeepSeek V4 Flashhigh87.3%57.2$0.0202026-09-01
17Kimi K3max87.2%60.2$0.1042026-09-01
18Qwen3.7max87.1%60.0$0.0872026-09-01
19Kimi K2.686.8%55.1$0.0652026-09-01
20GPT-5 minihigh86.6%54.6$0.0122026-09-01
21GPT-5.1high86.5%57.5$0.1262026-09-01
22Gemini 3 Pro86.4%60.0$0.1272026-09-01
23Nemotron 3 Ultra 550B A55B86.0%55.4–2026-09-01
24Qwen3.6 Plus86.0%59.0$0.0782026-09-01
25GPT-5.6 Terraxhigh85.9%60.1$0.0312026-09-01
26Inkling Small85.9%52.0$0.0212026-09-01
27Muse Spark 1.1xhigh85.9%59.5$0.0462026-09-01
28GPT-5high85.9%58.2$0.0642026-09-01
29Gemini 3 Flashhigh85.6%57.4$0.0512026-09-01
30GPT-5.1-Codex85.5%–$0.1382026-09-01
31Inkling85.5%50.4$0.1532026-09-01
32GPT-5.2xhigh85.4%59.9$0.1352026-09-01
33Qwen3.5 Plusthinking85.3%57.4$0.0482026-09-01
34GPT-5.5xhigh85.3%64.1$0.0672026-09-01
35Claude Opus 4.7max85.1%59.7$0.3512026-09-01
36GPT-5-Codexhigh84.7%58.6$0.0972026-09-01
37Claude Opus 4.6max84.7%57.0$0.3432026-09-01
38Grok 4.3high84.5%56.5$0.0202026-09-01
39Grok 4.20thinking84.3%58.3$0.0522026-09-01
40GPT-5.4xhigh84.1%63.1$0.3292026-09-01
41GPT-5.4 Nanohigh84.0%48.3$0.00252026-09-01
42Qwen3.8 27Bxhigh84.0%52.2$0.0452026-09-01
43Ling 3.0 Flash84.0%51.7$0.00302026-09-01
44o3high83.9%55.1$0.0332026-09-01
45Kimi K2.5thinking83.9%59.4$0.0392026-09-01
46Claude Opus 4.5high83.7%59.7$0.9712026-09-01
47GPT-5.1-Codex-Maxmax83.6%––2026-09-01
48Qwen3.5 Flash83.3%51.8$0.00952026-09-01
49Grok 483.3%58.1$0.1562026-09-01
50gpt-oss-120b83.2%46.1$0.00852026-09-01
51GPT-5.6 Solmax82.6%65.3$0.0902026-09-01
52Claude Sonnet 5max82.4%56.1$0.0952026-09-01
53GLM 4.782.2%51.7$0.0352026-09-01
54o4-minihigh82.2%51.2$0.0142026-09-01
55MiniMax M382.2%56.1$0.0372026-09-01
56Claude Sonnet 4.6max82.1%56.1$0.3712026-09-01
57Kimi K2.7 Code82.0%53.9$0.0272026-09-01
58GLM-5thinking81.9%60.2$0.0442026-09-01
59MiniMax-M2.181.8%53.8$0.0182026-09-01
60MiMo-V2.581.5%56.3$0.00222026-09-01

AI coding benchmark leaderboard · All LLM benchmarks

Cite as: BenchLeader, “LiveCodeBench leaderboard”, data as of 15 Nov 2026, https://www.benchleader.com/benchmarks/vals_livecodebench.

LiveCodeBench: questions

What does LiveCodeBench measure?
LiveCodeBench collects competitive-programming problems published after each model's training cutoff and checks solutions by running hidden tests. Scores are reported in percent of tasks solved; higher is better.
What is the top score on LiveCodeBench?
As of 15 Nov 2026, the highest score on LiveCodeBench is 90.5% by Claude Fable 5.1 (result dated 1 Sep 2026), ahead of Claude Fable 5 at 89.8%. Scores come from Vals AI and are re-read daily.
Which AI model leads LiveCodeBench?
Claude Fable 5.1 leads LiveCodeBench with 90.5% as of 15 Nov 2026 (result dated 1 Sep 2026), ahead of Claude Fable 5 at 89.8%.
How many models have LiveCodeBench results?
140 model configurations have a LiveCodeBench result on BenchLeader, all taken from Vals AI.
Who runs LiveCodeBench and how often is it updated?
LiveCodeBench is published by Vals AI. BenchLeader re-reads the published results once a day and records the date each result was published.
Does LiveCodeBench count toward the BenchLeader Index?
Yes. LiveCodeBench contributes to the coding category of the BenchLeader Index, normalised so that 50 is the average of the evaluated models.