AICoder
2026 Live Verified

AI Coding Models Leaderboard

Aggregated mirrors of 7 official benchmark boards and real-world coding task scenarios. 100% verified, objective, and zero paid placement.

7Boards
105Models ranked
4Evaluation Tasks
October 2026Period
2026-10-07Last update
●We fetch raw rankings from 5 public benchmark providers across 7 official boards — no re-weighting, no composite score. Click "Open official board" on each card to go to the source.
🧩Tool Matrix⚔️VS Compare
ADSponsored

📌 7 official boards · mirrored 1:1

Each card previews a provider's Top 5. Click "View full" for the complete board, or jump to the official page. Data is 100% from each provider — we do no aggregation or math.

LMArena Code ★
Human preference blind battle coding Elo leaderboard
Coding
Metric:Coding Elo· 53 models
  1. #1Claude Opus 5.51813.6
  2. #2GPT-6 Astra1787.6
  3. #3Claude Sonnet 5.51772.8
  4. #4GPT-6.1 Sol1757.3
  5. #5Claude Fable 5.11744.8
Official ↗
LMArena Agent
Human preference on real agentic coding sessions
Agent
Metric:Agent Score· 36 models
  1. #1Claude Fable 5.114.31
  2. #2Claude Opus 5.513.82
  3. #3Claude Sonnet 5.512.52
  4. #4GPT-6 Astra12.27
  5. #5GPT-6.1 Sol11.23
Official ↗
CursorBench
Cursor's first-party agentic coding benchmark (v4.0)
Agent
Metric:Pass rate%· 12 models
  1. #1Claude Opus 5.557.8%
  2. #2Claude Fable 5.151.8%
  3. #3Claude Opus 546.6%
  4. #4Grok 4.746.3%
  5. #5GPT-5.6 Sol41.7%
Official ↗
Artificial Analysis
Independent industry standard Intelligence Index
Overall
Metric:Intelligence Index· 99 models
  1. #1Claude Opus 5.557.6
  2. #2Claude Sonnet 5.556
  3. #3Claude Fable 5.153.4
  4. #4GPT-6 Astra52.7
  5. #5Gemini 4 Argon52.6
Official ↗
Vals AI
Independent evaluations on real-world tasks in software, finance & cybersecurity
Overall
Metric:Accuracy%· 32 models
  1. #1Gemini 4 Argon68.9%
  2. #2Claude Sonnet 5.567.0%
  3. #3Claude Opus 5.567.0%
  4. #4Claude Fable 5.165.8%
  5. #5Claude Opus 563.7%
Official ↗
LiveBench
Contamination-resistant coding suite (completion, generation, JS, Python, TS)
Coding
Metric:Score%· 46 models
  1. #1Claude Fable 5.183.4%
  2. #2Claude Opus 5.583.2%
  3. #3Claude Fable 583.0%
  4. #4GPT-6 Astra82.2%
  5. #5Muse Spark 1.381.6%
Official ↗
LMArena Text
Chatbot Arena text and general capability Elo rating
Chat
Metric:Arena Elo· 91 models
  1. #1Gemini 4 Argon1525.2
  2. #2Claude Opus 4.81504.7
  3. #3Claude Fable 51504.3
  4. #4Claude Opus 5.51503.7
  5. #5Claude Fable 5.11501.1
Official ↗

LMArena CodeCoding

Metric: Coding Elo·53 models·fetched 2026-10-07

Open official board ↗
✨

Not sure which model fits your budget & stack?

Try 4-Way Plan Showdowns & $20/mo vs API Cost Break-Even Meter

Compare Plans & Costs↗
#ModelCoding EloValue ScoreCross-board ranksActions
#1
Claude Opus 5.5Anthropic
1813.6
19.4
L #2
C #1
A #1
V #3
L #2
L #4
⚔️ VS💰Plans🚀Try
#2
GPT-6 AstraOpenAI
1787.6
7.8
L #4
C—
A #4
V #6
L #4
L #20
⚔️ VS💰Plans🚀Try
#3
Claude Sonnet 5.5Anthropic
1772.8
39.1
L #3
C—
A #2
V #2
L #18
L #27
⚔️ VS💰Plans🚀Try
#4
GPT-6.1 SolOpenAI
1757.3
38.1
L #5
C—
A #6
V #8
L #6
L #14
⚔️ VS💰Plans🚀Try
#5
Claude Fable 5.1Anthropic
1744.8
7.5
L #1
C #2
A #3
V #4
L #1
L #5
⚔️ VS💰Plans🚀Try
#6
Claude Opus 5Anthropic
1691.8
4.6
L #7
C #3
A #7
V #5
L #10
L #8
⚔️ VS💰Plans🚀Try
#7
GPT-6 SolOpenAI
1687.5
35.6
L #6
C—
A #10
V #11
L #12
L #36
⚔️ VS💰Plans🚀Try
#8
Gemini 4 ArgonGoogle
1678.4
37.8
L #9
C—
A #5
V #1
L—
L #1
⚔️ VS💰Plans🚀Try
#9
Qwen3.8-MaxQwen
1672.2
44
L #21
C—
A #13
V #25
L #14
L #16
⚔️ VS💰Plans🚀Try
#10
Muse Spark 1.3Meta
1656.1
63.1
L #17
C #11
A #9
V #9
L #5
L #7
⚔️ VS💰Plans🚀Try
#11
Kimi K3Moonshot AI
1655
22.2
L #13
C—
A #16
V #23
L #11
L #9
⚔️ VS💰Plans🚀Try
#12
Grok 4.7xAI
1638
41.7
L #15
C #4
A #12
V #13
L #20
L #46
⚔️ VS💰Plans🚀Try
#13
Hunyuan-T1Tencent
1631.7
479.1
L #18
C—
A #46
V #24
L—
L #38
⚔️ VS💰Plans🚀Try
#14
Claude Fable 5Anthropic
1624.1
7.2
L #8
C—
A #8
V #7
L #3
L #3
⚔️ VS💰Plans🚀Try
#15
GLM-5.3Zhipu AI
1622.3
60.5
L #22
C—
A #14
V #15
L #24
L #18
⚔️ VS💰Plans🚀Try
#16
DeepSeek-V4-FlashDeepSeek
1618.6
392.3
L #16
C—
A #22
V #20
L #7
L #25
⚔️ VS💰Plans🚀Try
#17
GPT-5.6 SolOpenAI
1617.8
11.5
L #11
C #5
A #11
V #10
L #8
L #13
⚔️ VS💰Plans🚀Try
#18
Grok 4.6xAI
1617
40.2
L #24
C #6
A #15
V #17
L #16
L #24
⚔️ VS💰Plans🚀Try
#19
GLM-5.2Zhipu AI
1603
60.1
L #19
C—
A #34
V—
L #32
L #21
⚔️ VS💰Plans🚀Try
#20
Qwen3.8-27BQwen
1592
268.5
L #31
C—
A #33
V—
L #28
L #50
⚔️ VS💰Plans🚀Try
#21
Gemini 3.7 FlashGoogle
1591.9
82
L #30
C—
A #21
V #21
L #13
L #10
⚔️ VS💰Plans🚀Try
#22
Gemini 3.8 FlashGoogle
1583.3
80.1
L #20
C #7
A #20
V #14
L #27
L #6
⚔️ VS💰Plans🚀Try
#23
GPT-6 LunaOpenAI
1582.3
601
L #23
C—
A #28
V #22
L #36
L #45
⚔️ VS💰Plans🚀Try
#24
DeepSeek-V4-ProDeepSeek
1581.9
121.8
L #26
C—
A #30
V #27
L #19
L #32
⚔️ VS💰Plans🚀Try
#25
Claude Opus 4.8Anthropic
1557.5
13.2
L #10
C—
A #19
V #12
L #23
L #2
⚔️ VS💰Plans🚀Try
#26
Grok 4.5xAI
1552.9
39.9
L #25
C—
A #24
V #29
L #26
L #29
⚔️ VS💰Plans🚀Try
#27
Claude Sonnet 5Anthropic
1540.9
28.7
L #12
C #9
A #27
V #18
L #25
L #33
⚔️ VS💰Plans🚀Try
#28
Gemini 3.6 FlashGoogle
1537.8
75.6
L #34
C—
A #32
V—
L #31
L #15
⚔️ VS💰Plans🚀Try
#29
Mistral Large 3Mistral AI
1533.8
39.5
L—C—
A #26
V #26
L #37
L #57
⚔️ VS💰Plans🚀Try
#30
Claude Sonnet 4.6Anthropic
1522.1
20.7
L—C—
A #36
V—
L #34
L #26
⚔️ VS💰Plans🚀Try
#31
GPT-5.6 TerraOpenAI
1521.5
25.5
L #28
C #8
A #18
V #16
L #17
L #30
⚔️ VS💰Plans🚀Try
#32
GPT-5.6 LunaOpenAI
1519.9
238.6
L #29
C #10
A #29
V #19
L #30
L #40
⚔️ VS💰Plans🚀Try
#33
Doubao Seed 2.0 ProByteDance
1518.9
120.6
L—C—
A #58
V—L—
L #37
⚔️ VS💰Plans🚀Try
#34
Qwen3.7-MaxQwen
1515.1
213
L #32
C—
A #38
V—
L #33
L #23
⚔️ VS💰Plans🚀Try
#35
GPT-5.5OpenAI
1512.7
17.5
L #14
C—
A #25
V—
L #9
L #17
⚔️ VS💰Plans🚀Try
#36
Kimi K2.6Moonshot AI
1509.1
74.2
L—C—
A #43
V—
L #38
L #34
⚔️ VS💰Plans🚀Try
#37
Gemini 3.5 FlashGoogle
1509.1
35
L—C—
A #35
V #28
L #29
L #19
⚔️ VS💰Plans🚀Try
#38
GLM-5.1Zhipu AI
1508.2
54.2
L—C—
A #44
V—L—
L #31
⚔️ VS💰Plans🚀Try
#39
MiniMax-M3MiniMax
1482.1
185.4
L #33
C—
A #39
V #30
L #44
L #49
⚔️ VS💰Plans🚀Try
#40
Qwen3.6-PlusQwen
1482
224.4
L—C—
A #40
V—
L #40
L #35
⚔️ VS💰Plans🚀Try
#41
Kimi K2.7 CodeMoonshot AI
1473.2
47.7
L—C—
A #45
V—
L #41
L—
⚔️ VS💰Plans🚀Try
#42
GPT-5.4OpenAI
1465.2
28.4
L #27
C—
A #23
V—
L #15
L #22
⚔️ VS💰Plans🚀Try
#43
Gemini 3.1 ProGoogle
1446.6
45.6
L #35
C—
A #37
V #31
L #21
L #11
⚔️ VS💰Plans🚀Try
#44
Gemini 3.5 Flash-LiteGoogle
1439.7
126.7
L—C—
A #53
V—
L #45
L #39
⚔️ VS💰Plans🚀Try
#45
Gemini 3 ProGoogle
1439.6
43.6
L—C—
A #41
V—L—
L #12
⚔️ VS💰Plans🚀Try
#46
GLM-4-PlusZhipu AI
1435.1
74
L—C—
A #52
V—L—
L #47
⚔️ VS💰Plans🚀Try
#47
MiniMax-M2.7MiniMax
1397.7
187.3
L—C—
A #51
V—L—
L #56
⚔️ VS💰Plans🚀Try
#48
GPT-5.4 miniOpenAI
1397.2
376.3
L—C—
A #48
V #32
L #39
L #41
⚔️ VS💰Plans🚀Try
#49
DeepSeek-V3DeepSeek
1362.2
543.8
L—C—
A #55
V—L—
L #54
⚔️ VS💰Plans🚀Try
#50
Grok 4.3xAI
1356.9
65.9
L—C—
A #47
V—
L #46
L #48
⚔️ VS💰Plans🚀Try
#51
Claude Haiku 4.5Anthropic
1329.7
59
L—C—
A #17
V—
L #35
L #58
⚔️ VS💰Plans🚀Try
#52
Mistral Medium 3.5Mistral AI
1263.3
81.2
L #36
C—
A #64
V—L—
L #52
⚔️ VS💰Plans🚀Try
#53
Gemini 2.5 ProGoogle
1227.7
23.5
L—C—
A #60
V—L—
L #42
⚔️ VS💰Plans🚀Try
Rank color:#1#2#3#4-5#6-10#11+

The "Cross-board ranks" column shows this model's rank on the other boards at a glance (grey = not tested there). Boards use different methodologies, so raw values are not directly comparable.

LMArena Code board: LMSYS Coding Arena Elo ratings based on real developer blind tests on challenging code prompts. Sourced directly from arena.ai/leaderboard/code and mirrored 1:1.

ADSponsored
📊 7 benchmark boards
LMArena Code ↗ Coding

LMArena Code board: LMSYS Coding Arena Elo ratings based on real developer blind tests on challenging code prompts. Sourced directly from arena.ai/leaderboard/code and mirrored 1:1.

Coding Elo53 models
LMArena Agent ↗ Agent

LMArena Agent board: real agentic coding sessions scored by human blind votes (signal-based agent score). Sourced from arena.ai/leaderboard/agent and mirrored 1:1.

Agent Score36 models
CursorBench ↗ Agent

CursorBench is Cursor's first-party agentic coding benchmark (v4.0). Tasks come from real Cursor sessions with ambiguous, multi-file requirements. Metric: pass rate (%). Mirrored from Cursor's official cursor.com/cursorbench snapshot.

Pass rate%12 models
Artificial Analysis ↗ Overall

Artificial Analysis Intelligence Index: Tracks reasoning, quality, and coding intelligence across 600+ models, continuously updated as new frontier models release.

Intelligence Index99 models
Vals AI ↗ Overall

Vals AI (Vals Index): Independent benchmarks evaluating frontier AI models on economically valuable real-world tasks across software, finance, cybersecurity, and agent autonomy. Metric: Accuracy (%). Sourced directly from vals.ai and mirrored 1:1.

Accuracy%32 models
LiveBench ↗ Coding

LiveBench Coding: Monthly refreshed contamination-resistant suite extracting code completion, generation, JavaScript, Python, and TypeScript performance.

Score%46 models
LMArena Text ↗ Chat

LMArena Text board: The global standard LMSYS Chatbot Arena tracking cross-domain text generation and complex instruction-following Elo ratings from arena.ai/leaderboard/text.

Arena Elo91 models

All rankings and numbers come directly from official sources; we only do name matching and aggregate presentation, no weighting or re-ranking. Boards use different methodologies, so do not compare raw values across boards.