LiveCodeBench leaderboard

Fresh competitive programming problems, collected after models’ training cut-offs to avoid contamination. Claude Fable 5.1 leads with 90.52%.

Models
126
Leader
Claude Fable 5.1
Source
Vals AI
As of
Oct 24, 2026
  1. 1Claude Fable 5.190.5%
  2. 2Claude Fable 589.8%
  3. 3Gemini 3.8 Flash89.5%
  4. 4Claude Opus 589.0%
  5. 5Gemini 3.7 Flash88.7%
  6. 6Gemini 3.1 Pro Preview88.5%
  7. 7Grok 4.688.2%
  8. 8Gemini 3.6 Flash88.1%
  9. 9GPT-5.2-Codex88.0%
  10. 10Qwen3.8-Max87.8%
LiveCodeBench, accuracy against cost per test
Open weightsProprietaryBest for the price
0%25%50%75%100%$.1$1$10Cost per test, log scale →Claude Fable 5.1Gemini 3.8 FlashDeepSeek-V4-FlashLing 3.0 FlashGPT-5 nano

Full leaderboard

RankModelLabAccuracyCost / testHarnessPrice in / out
1Claude Fable 5.1Anthropic90.52%$10 / $50—$10 / $50
2Claude Fable 5Anthropic89.78%$10 / $50—$10 / $50
3Gemini 3.8 FlashGoogle89.48%$1.5 / $7.5—$0.82 / $4.13
4Claude Opus 5Anthropic89.03%$5 / $25—$5 / $25
5Gemini 3.7 FlashGoogle88.65%$1.5 / $7.5—$0.75 / $3.75
6Gemini 3.1 Pro PreviewGoogle88.48%$2 / $12—$2 / $12
7Grok 4.6xAI88.22%$2 / $6—$2 / $6
8Gemini 3.6 FlashGoogle88.08%$1.5 / $7.5—$0.75 / $3.75
9GPT-5.2-CodexOpenAI87.99%$1.75 / $14—$1.75 / $14
10Qwen3.8-MaxAlibaba87.85%$2 / $6—$2 / $6
11Claude Opus 4.8Anthropic87.82%$5 / $25—$5 / $25
12Gemini 3.5 FlashGoogle87.60%$1.5 / $9—$1.50 / $9
14DeepSeek-V4-ProDeepSeek87.48%$1.32 / $3.96—$0.66 / $1.98
15Grok 4.5xAI87.35%$2 / $6—$2 / $6
16GPT-5.3-CodexOpenAI87.31%$1.75 / $14—$1.75 / $14
17DeepSeek-V4-FlashDeepSeek87.26%$0.44 / $1.32—$0.042 / $0.18
18Kimi K3Moonshot AI87.19%$3 / $15—$0.24 / $11
19Qwen3.7-Max-PreviewAlibaba87.06%$2.5 / $7.5—$1.48 / $4.42
20Kimi K2.6Moonshot AI86.77%$0.95 / $4—$0.65 / $3.41
21GPT-5 miniOpenAI86.61%$0.25 / $2—$0.25 / $2
22GPT-5.1OpenAI86.49%$1.25 / $10—$1.25 / $10
23Gemini 3 ProGoogle86.41%$2 / $12——
24Nemotron 3 UltraNVIDIA85.98%N/A—$0.60 / $2.40
25Qwen3.6-PlusAlibaba85.95%$0.5 / $3—$0.33 / $1.95
26Inkling-SmallThinky85.93%$0.3 / $1.2—$0.45 / $1.20
27GPT-5.6 TerraOpenAI85.93%$2 / $12—$2 / $12
28GPT-5OpenAI85.91%$1.25 / $10—$1.25 / $10
29Muse Spark 1.1Meta85.91%$1.25 / $4.25—$1.25 / $4.25
30Gemini 3 FlashGoogle85.59%$0.5 / $3—$0.50 / $3
31GPT-5.1-CodexOpenAI85.55%$1.25 / $10—$1.25 / $10
32InklingThinky85.52%$1 / $4.05—$1 / $4.05
33GPT-5.2OpenAI85.36%$1.75 / $14—$1.75 / $14
34Qwen 3.5 PlusAlibaba85.33%$0.4 / $2.4—$0.30 / $1.80
35GPT-5.5OpenAI85.30%$5 / $30—$5 / $30
36Claude Opus 4.7Anthropic85.07%$5 / $25—$5 / $25
37GPT 5 CodexOpenAI84.72%$1.25 / $10——
38Claude Opus 4.6Anthropic84.68%$5 / $25—$5 / $25
39Grok 4.3xAI84.49%$1.25 / $2.5—$1.25 / $2.50
40Grok 4.20xAI84.27%$2 / $6—$1.25 / $2.50
41GPT-5.4OpenAI84.14%$2.5 / $15—$2.50 / $15
42GPT-5.4 nanoOpenAI84.01%$0.2 / $1.25—$0.20 / $1.25
43Qwen3.8-27BAlibaba84.00%$0.5 / $3—$0.20 / $2.50
44Ling 3.0 FlashinclusionAI83.99%$0.075 / $0.22—$0.021 / $0.063
45o3OpenAI83.91%$2 / $8—$2 / $8
46Kimi K2.5Moonshot AI83.87%$0.6 / $3—$0.50 / $2.50
48GPT 5.1 Codex MaxOpenAI83.56%$1.25 / $10—$1.25 / $10
49Qwen3.5-FlashAlibaba83.28%$0.1 / $0.4—$0.065 / $0.26
50Grok 4xAI83.25%$3 / $15——
51gpt-oss-120bOpenAI83.23%$0.15 / $0.6—$0.15 / $0.60
52GPT-5.6 SolOpenAI82.60%$4 / $20—$4 / $20
53Claude Sonnet 5Anthropic82.43%$2 / $10—$2 / $10
54GLM-4.7Z.ai82.23%$0.6 / $2.2—$0.54 / $1.98
55o4-miniOpenAI82.21%$1.1 / $4.4—$1.10 / $4.40
56MiniMax-M3MiniMax82.15%$0.6 / $2.4—$0.30 / $1.20
57Claude Sonnet 4.6Anthropic82.09%$3 / $15—$3 / $15
58Kimi K2.7 CodeMoonshot AI82.05%$0.95 / $4—$0.67 / $3.35
59GLM-5Z.ai81.87%$1 / $3.2—$1 / $3.20
60MiniMax-M2.1 PreviewMiniMax81.76%$0.3 / $1.2—$0.30 / $1.20
61MiMo-V2.5Xiaomi81.51%$0.14 / $0.28—$0.12 / $0.24
62GPT-5.4 miniOpenAI81.47%$0.75 / $4.5—$0.75 / $4.50
63GLM-5.1Z.ai81.38%$1 / $3.2—$1.40 / $4.40
64MiMo-V2.5-ProXiaomi81.35%$0.435 / $0.87—$0.30 / $0.61
65GLM-4.6Z.ai81.04%$0.6 / $2.2—$0.55 / $2.20
67Grok 4.1 FastxAI80.64%$0.2 / $0.5——
68GLM-5.3Z.ai80.53%$1.4 / $4.4—$0.079 / $1.40
69GLM-5.3-FlashZ.ai80.51%$0.075 / $0.25—$0.15 / $0.50
70gpt-oss-20bOpenAI80.39%$0.07 / $0.3—$0.018 / $0.09
71Gemini 3.1 Flash-Lite PreviewGoogle80.12%$0.25 / $1.5—$0.25 / $1.50
72MiniMax-M2.7MiniMax79.93%$0.3 / $1.2—$0.30 / $1.20
73MiniMax-M2.5MiniMax79.21%$0.3 / $1.2—$0.30 / $1.20
74Gemini 2.5 ProGoogle79.16%$1.25 / $10—$1.25 / $10
75Gemini 3.5 Flash-LiteGoogle79.01%$0.3 / $2.5—$0.30 / $2.50
81Claude Opus 4.5Anthropic75.03%$5 / $25—$5 / $25
82Magistral MediumMistral AI74.86%$2 / $5——
83Claude Sonnet 4.5Anthropic73.00%$3 / $15—$3 / $15
85o3-miniOpenAI71.48%$1.1 / $4.4—$1.10 / $4.40
87Qwen3-235B-A22BAlibaba70.62%$0.22 / $0.88—$0.09 / $0.55
88Kimi K2 InstructMoonshot AI70.45%$1 / $3——
89DeepSeek-R1DeepSeek70.22%$1.35 / $5.4—$0.50 / $2.15
90GPT-5 nanoOpenAI70.22%$0.05 / $0.4—$0.05 / $0.40
92DeepSeek-V3.2-ExpDeepSeek69.86%$0.56 / $1.68—$0.28 / $0.42
93GLM-5.2Z.ai69.50%$1.4 / $4.4—$0.034 / $7
94Laguna M.1Poolside68.12%N/A——
95Laguna XS.2Poolside67.80%N/A——
96Gemini 2.5 Flash PreviewGoogle67.67%$0.1 / $0.4——
97GLM-4.5Z.ai67.45%$0.6 / $2.2—$0.60 / $2.20
98Qwen3-Max-PreviewAlibaba66.91%$1.2 / $6——
100Grok 3 Mini ReasoningxAI66.27%$0.3 / $0.5——
101DeepSeek-V3DeepSeek65.48%$0.9 / $0.9—$0.29 / $1.14
102Claude Opus 4.1Anthropic64.56%$15 / $75—$15 / $75
103Kimi K2 ThinkingMoonshot AI63.15%$0.6 / $2.5—$0.60 / $2.50
104Claude Opus 4Anthropic62.63%$15 / $75——
106Grok Code Fast 1xAI61.97%$0.2 / $1.5——
108Claude Sonnet 4Anthropic59.67%$3 / $15——
110GPT-4.1 miniOpenAI58.16%$0.4 / $1.6—$0.40 / $1.60
112Claude 3.7 SonnetAnthropic56.66%$3 / $15——
114GPT-4.1OpenAI54.67%$2 / $8—$2 / $8
115Grok 3 PreviewxAI52.90%$3 / $15——
116Devstral 2Mistral AI51.84%$0.4 / $2—$0.40 / $2
117o1OpenAI50.26%$15 / $60—$15 / $60
118Claude 3.5 SonnetAnthropic49.63%$3 / $15——
119Llama 4 MaverickFireworks AI47.25%$0.22 / $0.88—$0.19 / $0.65
120Gemini 2.5 Flash Preview 4/17Google46.87%$0.3 / $2.5——
121Grok 4 FastxAI46.09%$0.2 / $0.5——
122Mistral MediumMistral AI44.84%$0.4 / $2——
123Gemini 2.0 FlashGoogle43.61%$0.1 / $0.4——
124GPT-4oOpenAI43.44%$2.5 / $10—$2.50 / $10
125Devstral Small 2Mistral AI43.18%$0.1 / $0.3——
126GPT-4.1 nanoOpenAI42.72%$0.1 / $0.4—$0.10 / $0.40
127Grok 4.1 Fast Non-ReasoningxAI42.62%$0.2 / $0.5——
128Claude 3.5 HaikuAnthropic41.92%$0.8 / $4——
129Gemini 1.5 ProGoogle41.72%$1.25 / $5——
130Claude Haiku 4.5Anthropic41.17%$1 / $5—$1 / $5
131Grok 2xAI38.68%$2 / $10——
132Llama 4 ScoutMeta38.54%$0.18 / $0.59—$0.10 / $0.30
133Mistral LargeMistral AI37.09%$2 / $6—$0.50 / $1.50
134Gemini 1.5 FlashGoogle36.91%$0.075 / $0.3——
135Llama 3.3 Instruct TurboMeta36.34%$0.88 / $0.88——
136Llama 3.3 Nemotron SuperMeta36.31%N/A——
137Command ACohere35.07%$2.5 / $10—$0.30 / $1.50
138Magistral Small 1.2Mistral AI31.82%$0.075 / $0.3——
139GPT-4o miniOpenAI26.42%$0.15 / $0.6—$0.15 / $0.60
140Jamba 1.6 LargeAI21 Labs22.32%$2 / $8——
141Command R+Cohere18.24%$2.5 / $10—$0.15 / $0.60
142Mistral SmallMistral AI15.78%$0.2 / $0.6——
143Jamba 1.6 MiniAI21 Labs9.92%$0.2 / $0.4——

Related leaderboards

Sources

  • Vals AI, as of Oct 24, 2026
  • Provider list prices, as of Oct 24, 2026

Every number on this page comes from these sources; models without a published number show none. Download the data. Cite as “Nexus Explorer, nexus.inc/models”.