activeCoding

LiveCodeBench

Metric: Pass@1Introduced: 2024

Continuously updated coding benchmark sourcing new problems from LeetCode, AtCoder, and Codeforces post-May 2023 to eliminate contamination. Evaluates code generation, self-repair, and execution prediction.

Models ranked

56

tracked on this benchmark

Score band

93.5 – 32.8

best → lowest tracked

Snapshot trend

+11.30

Jul 1 → Aug 14 · 1 models

Leaderboard

Tracked models ranked by Pass@1 (higher is better).

Compare candidates
#Model variant and provenanceScore
1
DeepSeek V4 Pro
Version: Think Max mode (pass@1)Harness: Not recordedEvaluator: Not recordedObserved: Jun 7, 2026Confidence: Not recordedSource
93.5
2
Gemini 3.1 Pro Preview
Version: Rank 1 on pricepertoken (pass@1)Harness: Not recordedEvaluator: Not recordedObserved: Jun 7, 2026Confidence: Not recordedSource
91.7
3
DeepSeek V4 Flash
Version: LiveCodeBench pass@1, V4-Flash Think MaxHarness: Not recordedEvaluator: Not recordedObserved: Jul 3, 2026Confidence: Not recordedSource
91.6
4
Qwen3.7-Max
Version: LiveCodeBench v6 (pass@1)Harness: Not recordedEvaluator: Not recordedObserved: Jun 7, 2026Confidence: Not recordedSource
91.6
5
GPT-5.5 Pro
Version: LiveCodeBench; approximate standard GPT-5.5 scoreHarness: Not recordedEvaluator: Not recordedObserved: Apr 24, 2026Confidence: Not recordedSource

Notes: Low-confidence secondary-source row; CodingFleet table marked the GPT-5.5 value as approximate.

91.0
6
Qwen3.8-27B
Version: LiveCodeBench v6Harness: Not recordedEvaluator: Not recordedObserved: Aug 14, 2026Confidence: Not recordedSource
90.3
7
Kimi K2.6
Version: v6Harness: Not recordedEvaluator: Not recordedObserved: Apr 20, 2026Confidence: Not recordedSource
89.6
8
Claude Opus 4.8
Version: LiveCodeBenchHarness: Not recordedEvaluator: Not recordedObserved: May 28, 2026Confidence: Not recordedSource

Notes: Secondary-source competitive-programming row.

88.8
9
ByteDance Doubao Seed 2.0 Pro
Version: v6Harness: Not recordedEvaluator: Not recordedObserved: Apr 27, 2026Confidence: Not recordedSource
87.8
10
ByteDance Doubao Seed 2.0 Code
Version: v6Harness: Not recordedEvaluator: Not recordedObserved: Apr 27, 2026Confidence: Not recordedSource
87.8
11
MAI-Thinking-1
Version: v6Harness: Not recordedEvaluator: Not recordedObserved: Jun 2, 2026Confidence: Not recordedSource

Notes: Microsoft AI technical report Table 11 result for MAI-Thinking-1.

87.7
12
o4-mini
Version: 2026-04 (high reasoning mode)Harness: Not recordedEvaluator: Not recordedObserved: Apr 14, 2026Confidence: Not recordedSource
87.3
13
Nemotron-Cascade-2-30B-A3B
Version: LiveCodeBench v6 (accuracy)Harness: Not recordedEvaluator: Not recordedObserved: Jun 7, 2026Confidence: Not recordedSource
87.2
14
Qwen3.6 Max Preview
Version: Ranked 10th of 120 on LiveCodeBench from DataLearner (pass@1)Harness: Not recordedEvaluator: Not recordedObserved: Jun 7, 2026Confidence: Not recordedSource
87.1
15
Qwen3.6-Plus
Version: LiveCodeBench v6 (pass@1)Harness: Not recordedEvaluator: Not recordedObserved: Jun 7, 2026Confidence: Not recordedSource
87.1
16
Step 3.5 Flash
Version: LiveCodeBench-V6 (accuracy%)Harness: Not recordedEvaluator: Not recordedObserved: Jun 7, 2026Confidence: Not recordedSource
86.4
17
o3
Version: v6 pass@1, independent Kaggle leaderboardHarness: Not recordedEvaluator: Not recordedObserved: Nov 13, 2025Confidence: Not recordedSource

Notes: DAT-5669: independent Kaggle benchmark row; most recent reliable o3 LiveCodeBench figure in the handoff.

85.5
18
Kimi K2.5
Version: LiveCodeBench v6 (pass@1)Harness: Not recordedEvaluator: Not recordedObserved: Jun 7, 2026Confidence: Not recordedSource
85.0
19
Qwen3.6-27B
Version: LiveCodeBench v6Harness: Not recordedEvaluator: Not recordedObserved: Apr 27, 2026Confidence: Not recordedSource
83.9
20
Qwen3.5-397B-A17B
Version: LiveCodeBench v6 (pass@1)Harness: Not recordedEvaluator: Not recordedObserved: Jun 7, 2026Confidence: Not recordedSource
83.6
21
OLMo 3 32B Think
Version: LiveCodeBench v3 (accuracy)Harness: Not recordedEvaluator: Not recordedObserved: Jun 7, 2026Confidence: Not recordedSource
83.5
22
Mistral Large 3 675B Instruct
Version: Not recordedHarness: Not recordedEvaluator: Not recordedObserved: Dec 1, 2025Confidence: Not recordedSource
82.8
23
GLM-5
Version: LiveCodeBench v6 (accuracy)Harness: Not recordedEvaluator: Not recordedObserved: Jun 7, 2026Confidence: Not recordedSource
81.9
24
ByteDance Doubao Seed 2.0 Lite
Version: v6Harness: Not recordedEvaluator: Not recordedObserved: Apr 27, 2026Confidence: Not recordedSource
81.7
25
Qwen3.5-27B
Version: LiveCodeBench v6 (pass@1)Harness: Not recordedEvaluator: Not recordedObserved: Jun 7, 2026Confidence: Not recordedSource
80.7
Showing the top 25 of 56 tracked models. Browse all models.

How to read this benchmark

This benchmark scores models where higher is better. Use scores for directional filtering and shortlisting, not universal quality ranking; then validate pricing, context window, provider availability, and fit for your workload.

Trust this score when

  • There is a fresh timestamped snapshot (or multiple snapshots) for this benchmark.
  • The model list covers the same version family you can actually deploy today.
  • Top candidates overlap with your required routing and feature requirements.

Be cautious when

  • There is only one benchmark snapshot or the dataset appears stale.
  • The benchmark metric direction is opposite of your decision objective.
  • The score difference between options is narrow and likely within implementation variance.

Related benchmarks

HumanEval
MBPP
Mostly Basic Programming Problems
HumanEval+
MBPP+
Mostly Basic Programming Problems+
Spider
ToolTalk

Last reviewed: Apr 15, 2026

Resources

WebsitearXiv PaperLeaderboard