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
107Models ranked
4Evaluation Tasks
October 2026Period
2026-10-14Last 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💳Plans
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
  2. #2GPT-6 Astra1786.1
  3. #3Claude Sonnet 5.51774.3
  4. #4GPT-6.1 Sol1755.4
  5. #5Claude Fable 5.11743.7
Official ↗
LMArena Agent
Human preference on real agentic coding sessions
Agent
Metric:Agent Score· 37 models
  1. #1Claude Opus 5.515.53
  2. #2GPT-6 Astra13.09
  3. #3Claude Fable 5.112.66
  4. #4Claude Sonnet 5.511.95
  5. #5GPT-6.1 Sol11.72
Official ↗
CursorBench
Cursor's first-party agentic coding benchmark (v4.0)
Agent
Metric:Pass rate%· 15 models
  1. #1Claude Opus 5.557.8%
  2. #2Claude Sonnet 5.555.5%
  3. #3Gemini 4 Argon52.9%
  4. #4Claude Fable 5.151.8%
  5. #5Claude Opus 546.6%
Official ↗
Artificial Analysis
Independent industry standard Intelligence Index
Overall
Metric:Intelligence Index· 101 models
  1. #1Claude Opus 5.557.6
  2. #2Claude Sonnet 5.556
  3. #3Muse Wonder Full55.8
  4. #4Claude Fable 5.153.4
  5. #5GPT-6 Astra52.7
Official ↗
Vals AI
Independent evaluations on real-world tasks in software, finance & cybersecurity
Overall
Metric:Accuracy%· 35 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. #5Muse Wonder Full64.6%
Official ↗
LiveBench
Contamination-resistant coding suite (completion, generation, JS, Python, TS)
Coding
Metric:Score%· 47 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 Argon1525.4
  2. #2Claude Opus 5.51507.1
  3. #3Claude Opus 4.81504.4
  4. #4Claude Fable 51503.7
  5. #5Claude Fable 5.11500.7
Official ↗

LMArena CodeCoding

Metric: Coding Elo·53 models·fetched 2026-10-12

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
19.4
L #1
C #1
A #1
V #3
L #2
L #2
⚔️ VS💰Plans🚀Try
#2
GPT-6 AstraOpenAI
1786.1
7.8
L #2
C—
A #5
V #7
L #4
L #23
⚔️ VS💰Plans🚀Try
#3
Claude Sonnet 5.5Anthropic
1774.3
36.8
L #4
C #2
A #2
V #2
L #19
L #20
⚔️ VS💰Plans🚀Try
#4
GPT-6.1 SolOpenAI
1755.4
37.9
L #5
C—
A #8
V #9
L #6
L #14
⚔️ VS💰Plans🚀Try
#5
Claude Fable 5.1Anthropic
1743.7
7.3
L #3
C #4
A #4
V #4
L #1
L #5
⚔️ VS💰Plans🚀Try
#6
Claude Opus 5Anthropic
1691.3
4.6
L #9
C #5
A #9
V #6
L #11
L #8
⚔️ VS💰Plans🚀Try
#7
GPT-6 SolOpenAI
1688.2
35.5
L #6
C—
A #12
V #13
L #13
L #37
⚔️ VS💰Plans🚀Try
#8
Gemini 4 ArgonGoogle
1677.8
35.6
L #7
C #3
A #6
V #1
L—
L #1
⚔️ VS💰Plans🚀Try
#9
Qwen3.8-MaxQwen
1673.5
43.9
L #21
C—
A #15
V #28
L #15
L #15
⚔️ VS💰Plans🚀Try
#10
Muse Spark 1.3Meta
1656.9
64.7
L #14
C #9
A #11
V #11
L #5
L #7
⚔️ VS💰Plans🚀Try
#11
Kimi K3Moonshot AI
1654.4
22.1
L #16
C—
A #18
V #26
L #12
L #9
⚔️ VS💰Plans🚀Try
#12
Grok 4.7xAI
1639.1
41.3
L #19
C #6
A #14
V #15
L #21
L #45
⚔️ VS💰Plans🚀Try
#13
Hunyuan-T1Tencent
1631.8
475.2
L #17
C—
A #49
V #27
L—
L #39
⚔️ VS💰Plans🚀Try
#14
Claude Fable 5Anthropic
1624.7
7.2
L #8
C—
A #10
V #8
L #3
L #4
⚔️ VS💰Plans🚀Try
#15
GLM-5.3Zhipu AI
1622.2
56.8
L #22
C #7
A #16
V #18
L #25
L #18
⚔️ VS💰Plans🚀Try
#16
DeepSeek-V4-FlashDeepSeek
1618.6
390.5
L #15
C—
A #24
V #23
L #8
L #26
⚔️ VS💰Plans🚀Try
#17
GPT-5.6 SolOpenAI
1618.3
11.4
L #11
C #8
A #13
V #12
L #9
L #13
⚔️ VS💰Plans🚀Try
#18
Grok 4.6xAI
1617.2
40.1
L #27
C #10
A #17
V #20
L #17
L #25
⚔️ VS💰Plans🚀Try
#19
GLM-5.2Zhipu AI
1603.2
59.7
L #18
C—
A #37
V—
L #33
L #21
⚔️ VS💰Plans🚀Try
#20
Qwen3.8-27BQwen
1592.8
267.6
L #30
C—
A #36
V—
L #29
L #50
⚔️ VS💰Plans🚀Try
#21
Gemini 3.7 FlashGoogle
1591.5
81.6
L #31
C—
A #23
V #24
L #14
L #11
⚔️ VS💰Plans🚀Try
#22
Claude Haiku 4.5Anthropic
1586.9
63.3
L—C—
A #19
V #17
L #36
L #58
⚔️ VS💰Plans🚀Try
#23
Gemini 3.8 FlashGoogle
1583.5
79.9
L #20
C #12
A #22
V #16
L #28
L #6
⚔️ VS💰Plans🚀Try
#24
DeepSeek-V4-ProDeepSeek
1582
121.8
L #24
C—
A #32
V #30
L #20
L #31
⚔️ VS💰Plans🚀Try
#25
GPT-6 LunaOpenAI
1580.9
602.4
L #23
C—
A #30
V #25
L #37
L #46
⚔️ VS💰Plans🚀Try
#26
Claude Opus 4.8Anthropic
1557.5
13.2
L #10
C—
A #21
V #14
L #24
L #3
⚔️ VS💰Plans🚀Try
#27
Grok 4.5xAI
1552.8
39.8
L #25
C—
A #26
V #32
L #27
L #30
⚔️ VS💰Plans🚀Try
#28
Mistral Large 3Mistral AI
1541.3
36.5
L #33
C—
A #28
V #29
L #38
L #52
⚔️ VS💰Plans🚀Try
#29
Claude Sonnet 5Anthropic
1540.8
28.7
L #12
C #14
A #29
V #21
L #26
L #33
⚔️ VS💰Plans🚀Try
#30
Gemini 3.6 FlashGoogle
1537.8
75.8
L #35
C—
A #35
V—
L #32
L #16
⚔️ VS💰Plans🚀Try
#31
Claude Sonnet 4.6Anthropic
1522.4
20.7
L—C—
A #39
V—
L #35
L #27
⚔️ VS💰Plans🚀Try
#32
GPT-5.6 TerraOpenAI
1521.8
25.7
L #28
C #11
A #20
V #19
L #18
L #29
⚔️ VS💰Plans🚀Try
#33
Doubao Seed 2.0 ProByteDance
1519.1
120.6
L—C—
A #61
V—L—
L #36
⚔️ VS💰Plans🚀Try
#34
GPT-5.6 LunaOpenAI
1519
240.6
L #29
C #13
A #31
V #22
L #31
L #40
⚔️ VS💰Plans🚀Try
#35
Qwen3.7-MaxQwen
1515.1
212.8
L #32
C—
A #41
V—
L #34
L #24
⚔️ VS💰Plans🚀Try
#36
GPT-5.5OpenAI
1512.7
17.5
L #13
C—
A #27
V—
L #10
L #17
⚔️ VS💰Plans🚀Try
#37
Gemini 3.5 FlashGoogle
1510.5
35
L—C—
A #38
V #31
L #30
L #19
⚔️ VS💰Plans🚀Try
#38
Kimi K2.6Moonshot AI
1509.1
74.2
L—C—
A #46
V—
L #39
L #34
⚔️ VS💰Plans🚀Try
#39
GLM-5.1Zhipu AI
1508.3
54.2
L—C—
A #47
V—L—
L #32
⚔️ VS💰Plans🚀Try
#40
Qwen3.6-PlusQwen
1482.3
224.4
L—C—
A #43
V—
L #41
L #35
⚔️ VS💰Plans🚀Try
#41
MiniMax-M3MiniMax
1481.7
186
L #34
C—
A #42
V #33
L #45
L #49
⚔️ VS💰Plans🚀Try
#42
Kimi K2.7 CodeMoonshot AI
1473.4
47.7
L—C—
A #48
V—
L #42
L—
⚔️ VS💰Plans🚀Try
#43
GPT-5.4OpenAI
1465.3
28.4
L #26
C—
A #25
V—
L #16
L #22
⚔️ VS💰Plans🚀Try
#44
Gemini 3.1 ProGoogle
1446.7
45.8
L #36
C—
A #40
V #34
L #22
L #10
⚔️ VS💰Plans🚀Try
#45
Gemini 3.5 Flash-LiteGoogle
1439.7
126.7
L—C—
A #56
V—
L #46
L #38
⚔️ VS💰Plans🚀Try
#46
Gemini 3 ProGoogle
1439.5
43.6
L—C—
A #44
V—L—
L #12
⚔️ VS💰Plans🚀Try
#47
GLM-4-PlusZhipu AI
1435
74
L—C—
A #55
V—L—
L #48
⚔️ VS💰Plans🚀Try
#48
MiniMax-M2.7MiniMax
1397.9
187.3
L—C—
A #54
V—L—
L #57
⚔️ VS💰Plans🚀Try
#49
GPT-5.4 miniOpenAI
1397.3
376.5
L—C—
A #51
V #35
L #40
L #41
⚔️ VS💰Plans🚀Try
#50
DeepSeek-V3DeepSeek
1362.2
543.4
L—C—
A #58
V—L—
L #55
⚔️ VS💰Plans🚀Try
#51
Grok 4.3xAI
1357.1
65.9
L—C—
A #50
V—
L #47
L #47
⚔️ VS💰Plans🚀Try
#52
Mistral Medium 3.5Mistral AI
1263.5
82.2
L #37
C—
A #66
V—L—
L #53
⚔️ VS💰Plans🚀Try
#53
Gemini 2.5 ProGoogle
1227.4
29.3
L—C—
A #33
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 Score37 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%15 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 Index101 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%35 models
LiveBench ↗ Coding

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

Score%47 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.