LLM Leaderboard

Daily AI model rankings: as of Oct 16, the top agent task success rate belongs to Claude Opus 5.5 (17.18%).

Data updated Oct 16, 2026
Arena published Oct 15
Agents board released Oct 14, 2026
84 models
Sources & methodology

Top agent

Claude Opus 5.517.18% Top in Text

Gemini 4 Argon1,523.9 Intelligence #1

Claude Opus 5.557.6 Coding #1

Claude Fable 5.181.6 Best value

MiMo-V2.6-Flash$0.28/1M out Open weights #1

Kimi K3Arena 1,487.1

This week

Daily Agents records started on Oct 16, 2026; rank changes appear after 14 days.

New models

last 14 days

LLM Leaderboard: full table

Showing 84 rows

Default order is the arena.ai Agents leaderboard task success rate (the tier used is shown). Models without an agent result follow, ordered by LMArena Text (style control). Success-rate intervals are wide, so neighbouring ranks are often within error. Sort by Text score instead →

#	Model	Agent	Text	AA index		Price $/1M tokens		Latency (s) & speed	Context	Released
#	Model	Agent	Text	Intel.	Coding	Input	Output	Lowest route	Context	Released	TTFT	Answer	tok/s
1	Claude Opus 5.5AnthropicClosed	17.18%Max Preliminary	1508.2±7.4	57.6	–	$4.00	$20.00	$4.00 / $20.00	450	450	98	1M	Sep 22
2	GPT-6.1 SolOpenAIClosed	14.78%Max	1483.8±8.2	51.8	–	$2.00	$10.00	$2.00 / $10.00	164	164	59	1.05M	Sep 29
3	Claude Fable 5.1AnthropicClosed	14.12%Max	1502.3±6.1	53.4	81.6	$10.00	$50.00	$10.00 / $50.00	137	137	66	1M	Sep 1
4	Gemini 4 Argon PreliminaryGoogleClosed	13.73%High	1523.9±8.8	52.6	–	$2.00	$10.00	$2.00 / $10.00	–	–	–	1.05M	Sep 30
5	GPT-6 AstraOpenAIClosed	13.69%Max	1477.3±6.3	52.7	76.9	$10.00	$50.00	$10.00 / $50.00	189	189	49	1.05M	Sep 3
6	Claude Sonnet 5.5AnthropicClosed	12.55%Max Preliminary	1474.9±7.8	56.0	–	$2.00	$10.00	$2.00 / $10.00	301	301	142	1M	Sep 28
7	GPT-6 SolOpenAIClosed	11.20%Max Preliminary	1459.0±6.4	47.6	–	$2.00	$10.00	$2.00 / $10.00	–	–	–	1.05M	Sep 22
8	Claude Opus 5AnthropicClosed	9.20%Max	1490.0±4.8	50.8	78.0	$5.00	$25.00	$5.00 / $25.00	–	–	–	1M	Jul 24
9	Claude Fable 5AnthropicClosed	8.39%High	1503.6±4.3	49.6	76.5	$10.00	$50.00	$10.00 / $50.00	–	–	–	1M	Jun 9
10	GPT-5.6 SolOpenAIClosed	7.42%XHigh	1484.7±4.4	47.0	77.4	$4.00	$20.00	$4.00 / $20.00	–	–	–	1.05M	Jul 9
11	Claude Opus 4.8AnthropicClosed	7.14%High	1481.5±3.9	41.8	74.3	$5.00	$25.00	$5.00 / $25.00	–	–	–	1M	May 28
12	Muse Wonder PreliminaryMetaClosed	6.42%Max Preliminary	1508.9±10.6	52.4	–	$4.00	$20.00	$4.00 / $20.00	33	45	174	1.05M	Oct 12
13	Claude Sonnet 5AnthropicClosed	4.69%High	1461.1±4.2	38.2	71.5	$2.00	$10.00	$2.00 / $10.00	–	–	–	1M	Jun 30
14	Gemini 3.8 FlashGoogleClosed	3.97%High	1496.4±4.6	40.9	76.3	$0.75	$3.75	$0.83 / $4.13	17	17	137	1.05M	Sep 2
15	MiMo-V2.6-Pro PreliminaryXiaomiOpen weights	3.81%	1479.2±9.4	46.3	–	$0.44	$0.87	$0.44 / $0.87	2.9	43	50	1.05M	Sep 21
16	Muse Spark 1.3MetaClosed	3.63%Max	1494.4±5.6	48.1	75.8	$1.25	$4.25	$1.25 / $4.25	46	61	135	1.05M	Sep 2
17	Grok 4.7xAIClosed	3.39%XHigh	1444.0±6.4	46.4	–	$2.00	$6.00	$2.00 / $6.00	21	21	84	500K	Sep 21
18	GPT-5.5OpenAIClosed	3.31%XHigh	1481.4±3.8	38.4	74.9	$5.00	$30.00	$5.00 / $30.00	–	–	–	1.05M	Apr 23
19	GPT-6 LunaOpenAIClosed	3.26%Max	1442.8±4.6	38.1	–	$0.10	$0.50	$0.10 / $0.50	103	103	128	1.05M	Sep 22
20	DeepSeek V4.1 FlashDeepSeekOpen weights	2.95%Max	1474.6±6.3	39.5	–	$0.30	$1.20	$0.036 / $0.68 ⚠	0.9	12	180	1.05M	Sep 10
21	MiMo-V2.6-FlashXiaomiOpen weights	2.53%	1450.9±6.5	37.9	–	$0.14	$0.28	$0.14 / $0.28	3.7	43	51	1.05M	Sep 21
22	GLM-5.2Z.AIOpen weights	2.35%Max	1475.9±4.2	33.7	68.8	$1.40	$4.40	$0.62 / $2.42	–	–	–	1.05M	Jun 16
23	GLM-5.3Z.AIOpen weights	2.00%Max	1478.5±5.3	44.8	74.8	$1.40	$4.40	$0.079 / $4.80 ⚠	3.0	31	71	1.05M	Aug 18
24	Kimi K3Moonshot AIOpen weights	1.95%Max	1487.1±4.6	43.6	76.2	$3.00	$15.00	$0.30 / $11.94 ⚠	2.8	47	45	1.05M	Jul 16
25	Qwen3.8 MaxAlibabaClosed	1.92%	1482.4±5.0	45.4	76.2	$2.00	$6.00	$2.00 / $6.00	1.7	54	38	1M	Sep 2
26	Claude Haiku 5.5Anthropic	1.88%High	–	37.8	–	$0.10	$0.50	$0.10 / $0.50	20	20	171	1M	Oct 7
27	GPT-5.4OpenAIClosed	1.64%High	1475.1±3.8	39.0	71.1	$2.50	$15.00	$2.50 / $15.00	–	–	–	1.05M	Mar 5
28	Grok 4.6xAIClosed	1.16%XHigh	1454.5±4.8	44.3	76.8	$2.00	$6.00	$2.00 / $6.00	–	–	–	500K	Aug 12
29	GPT-5.6 TerraOpenAIClosed	0.43%XHigh	1466.4±4.3	42.1	76.7	$2.00	$12.00	$2.00 / $12.00	105	105	116	1.05M	Jul 9
30	DeepSeek V4 ProDeepSeekOpen weights	0.36%High Preliminary	1464.6±6.6	36.0	68.8	$1.32	$3.96	$0.96 / $1.91	1.2	23	93	1.05M	Aug 13
31	Grok 4.5xAIClosed	0.07%	1465.7±4.3	38.8	72.4	$2.00	$6.00	$2.00 / $6.00	–	–	–	500K	Jul 8
32	Gemini 3.7 FlashGoogleClosed	-0.41%High	1487.6±4.9	39.6	71.5	$0.75	$3.75	$0.75 / $3.75	–	–	–	1.05M	Aug 13
33	GLM-5.3 FlashZ.AIOpen weights	-1.09%	1473.8±4.9	41.8	71.5	$0.15	$0.50	$0.021 / $0.90 ⚠	2.4	34	63	1.05M	Aug 26
34	SStep 5 PreviewStepFunClosed	-1.33%	1447.3±7.5	43.7	–	$1.00	$2.70	–	1.4	25	86	–	Sep 18
35	GPT-5.6 LunaOpenAIClosed	-1.80%XHigh	1452.6±4.3	37.3	71.4	$0.20	$1.20	$0.20 / $1.20	–	–	–	1.05M	Jul 9
36	Qwen3.8-Flash-NextAlibaba	-2.56%	–	39.8	73.1	$0.15	$0.47	–	1.3	43	48	–	Aug 26
37	Mistral Large 4 PreviewMistralClosed	-3.15%	1431.8±7.3	38.4	–	$1.36	$4.18	–	–	–	–	–	Oct 6
38	Qwen3.8 27BAlibabaOpen weights	-3.21%	1437.8±5.2	33.7	68.1	$0.50	$3.00	$0.24 / $2.20	1.3	51	40	1M	Aug 14
39	Gemini 3.1 Pro PreviewGoogleClosed	-3.53%	1486.9±3.0	29.7	68.8	$2.00	$12.00	$2.00 / $12.00	20	20	139	1.05M	Feb 19
40	Gemini 3.6 FlashGoogleClosed	-4.72%High	1482.7±4.4	34.0	69.2	$0.75	$3.75	$0.75 / $3.75	–	–	–	1.05M	Jul 21
41	Qwen3.7 Max PreliminaryAlibabaClosed	-5.80%	1474.3±9.8	29.5	66.0	$2.50	$7.50	$1.48 / $4.43	–	–	–	1M	May 19
42	Hy3TencentOpen weights	-6.13%	1453.2±6.2	25.3	58.8	$0.14	$0.56	$0.13 / $0.53	1.9	25	87	262K	Jul 6
43	Muse Spark 1.1MetaClosed	-6.25%	1490.2±4.3	33.7	71.3	$1.25	$4.25	$1.25 / $4.25	–	–	–	1.05M	Jul 9
44	Qwen3.7 PlusAlibabaClosed	-6.35%	1455.7±4.3	25.2	55.9	$0.40	$1.60	$0.32 / $1.28	1.7	38	55	1M	Jun 1
45	Muse Spark 1.2MetaClosed	-6.52%XHigh	1493.1±7.2	39.6	72.2	$1.25	$4.25	$1.25 / $4.25	–	–	–	1.05M	Aug 5
46	MiMo V2.5 ProXiaomiOpen weights	-7.67%	1467.3±3.6	26.0	60.2	$0.44	$0.87	$0.44 / $0.87	–	–	–	1.05M	Apr 22
47	MiniMax M3MiniMaxOpen weights	-7.86%	1441.3±3.9	29.2	58.6	$0.30	$1.20	$0.30 / $1.20	0.9	20	102	1.05M	Jun 1
48	Mistral Medium 3.5MistralOpen weights	-11.33%	1426.5±6.4	14.2	46.9	$1.50	$7.50	$1.50 / $7.50	0.7	13	168	262K	Apr 29
The 36 models below have no Agents result yet and are ordered by Text score
49	Claude Opus 4.6AnthropicClosed	–	1503.1±3.4	31.9	–	$5.00	$25.00	$5.00 / $25.00	–	–	–	1M	Feb 5
50	Claude Opus 4.7AnthropicClosed	–	1501.1±3.8	40.7	73.6	$5.00	$25.00	$5.00 / $25.00	–	–	–	1M	Apr 16
51	Muse SparkMetaClosed	–	1489.0±5.8	31.3	58.6	–	–	–	–	–	–	–	Apr 8
52	Gemini 3 ProGoogleClosed	–	1485.5±3.8	28.0	–	$2.00	$12.00	–	–	–	–	–	Nov 18, 2025
53	Gemini 3.5 FlashGoogleClosed	–	1477.5±3.9	33.6	–	$1.50	$9.00	$1.50 / $9.00	–	–	–	1.05M	May 19
54	GPT-5.2 ChatOpenAIClosed	–	1475.6±4.1	–	–	$1.75^*	$14.00^*	$1.75 / $14.00	–	–	–	128K	Dec 10, 2025
55	Gemini 3 FlashGoogleClosed	–	1472.8±4.3	26.3	–	$0.50	$3.00	$0.50 / $3.00	–	–	–	1.05M	Dec 17, 2025
56	Claude Sonnet 4.6AnthropicClosed	–	1472.1±3.5	30.1	63.0	$3.00	$15.00	$3.00 / $15.00	–	–	–	1M	Feb 17
57	Grok 4.20xAIClosed	–	1471.5±3.7	25.7	–	$1.25	$2.50	$1.25 / $2.50	–	–	–	2M	Apr 7
58	Claude Opus 4.5AnthropicClosed	–	1469.6±3.2	29.1	–	$5.00	$25.00	$5.00 / $25.00	–	–	–	200K	Nov 24, 2025
59	GLM-5.1Z.AIOpen weights	–	1465.2±3.6	26.1	55.8	$1.29	$4.07	$0.97 / $3.04	–	–	–	205K	Apr 7
60	Kimi K2.6Moonshot AIOpen weights	–	1460.8±4.5	27.0	61.8	$0.95	$4.00	$0.65 / $3.41	–	–	–	262K	Apr 20
61	Qwen3.6 MaxAlibabaClosed	–	1460.6±8.2	28.4	–	–	–	–	–	–	–	–	Apr 20
62	GLM-5Z AIOpen weights	–	1457.3±4.3	27.9	–	$1.00	$3.20	$1.00 / $3.20	–	–	–	205K	Feb 11
63	GPT-5.1OpenAIClosed	–	1455.7±3.7	24.7	49.4	$1.25	$10.00	$1.25 / $10.00	–	–	–	400K	Nov 13, 2025
64	Kimi K2.5Moonshot AIOpen weights	–	1449.8±3.3	23.5	46.8	$0.60	$2.75	$0.50 / $2.50	–	–	–	262K	Jan 27
65	Gemini 2.5 ProGoogleClosed	–	1445.4±2.5	16.1	33.3	$1.25	$10.00	$1.25 / $10.00	–	–	–	1.05M	Jun 5, 2025
66	DeepSeek V4 FlashDeepSeekOpen weights	–	1438.7±4.1	34.3	69.1	$0.44	$1.32	$0.091 / $0.18 ⚠	–	–	–	1.05M	Jul 31
67	GPT-5.2OpenAIClosed	–	1437.2±3.6	30.4	–	$1.75	$14.00	$1.75 / $14.00	–	–	–	400K	Dec 11, 2025
68	MiMo V2.5XiaomiOpen weights	–	1433.8±4.2	21.8	56.8	$0.14	$0.28	$0.14 / $0.28	–	–	–	1.05M	Apr 22
69	DeepSeek V3.2DeepSeekOpen weights	–	1424.6±3.5	21.5	44.2	$0.28	$0.42	$0.26 / $0.80	–	–	–	164K	Dec 1, 2025
70	GLM-4.6Z AIOpen weights	–	1424.1±3.9	18.5	45.8	$0.58	$2.20	$0.50 / $2.00	–	–	–	205K	Sep 30, 2025
71	Qwen3 MaxAlibabaClosed	–	1423.4±6.5	15.6	–	–	–	–	–	–	–	–	Sep 23, 2025
72	CJT-4.1 Flash 236B A21BChina Mobile	–	–	27.3	52.4	–	–	–	–	–	–	–	Jul 9
73	DeepSeek V4 Flash VisionDeepSeek	–	–	34.8	65.0	$0.44	$1.32	–	1.0	12	176	–	Aug 21
74	DeepSeek V4 Pro 0424DeepSeek	–	–	30.1	58.7	$0.44	$0.87	–	–	–	–	–	Apr 24
75	ILing 3.1 FlashInclusionAI	–	–	41.1	–	$0.30	$0.90	$0.075 / $0.23 ⚠	1.1	10	217	262K	Oct 1
76	IK2 Horizon 375B A23BInstitute of Foundation Models	–	–	30.5	61.5	–	–	–	1.7	3.7	1021	–	Sep 3
77	Muse Spark OpenMetaOpen weights	–	–	38.9	–	$1.25	$4.25	$1.25 / $4.25	0.5	20	105	1.05M	Oct 15
78	Muse Wonder FullMeta	–	–	55.8	–	–	–	–	–	–	–	–	Oct 12
79	Mistral LargeMistral	–	–	5.8	–	$4.00	$12.00	$2.00 / $6.00	–	–	–	128K	Feb 26, 2024
80	Kimi K2.7 CodeMoonshot AIOpen weights	–	–	25.8	60.8	$0.95	$4.00	$0.67 / $3.35	1.2	44	52	262K	Jun 12
81	MMotif 3Motif Technologies	–	–	33.6	63.5	–	–	–	–	–	–	–	Aug 12
82	GPT-5.3 CodexOpenAI	–	–	32.5	–	$1.75	$14.00	$1.75 / $14.00	61	61	94	400K	Feb 5
83	Qwen3.8 2.4T A95BAlibabaOpen weights	–	–	39.9	71.9	$2.00	$6.00	$2.00 / $6.00	2.0	54	38	1.05M	Aug 12
84	SAgnes 2.5 Pro BetaSapiens AI	–	–	35.2	62.3	$0.10	$0.30	–	0.7	17	120	–	Aug 26

Arena scores are LMArena's Bradley-Terry scale (not Elo). Input/output prices are official API list prices per million tokens; the lowest route price is the cheapest OpenRouter quote. In this view the median Arena margin is ±4.4 while neighbouring models sit a median 1.0 apart (68 of 68 adjacent pairs overlap): gaps under 4.4 say nothing about which model ranks higher.

One row per model: each row uses that model’s best tier for the column you sorted by (best of the tiers that have a measurement, ties going to the stronger tier). Arena scores and prices are model-level, so every tier of a model shares them. Switch to “Each tier” to see each reasoning tier on its own row.

Not yet ranked by Arena 2

Tracked models that have no LMArena or Artificial Analysis score yet, newest first. They move into the table once scored.

On the Agents board, not yet in our catalogue 5

These models have an arena.ai Agents result but no model page here yet (no price data), so they are not ranked in the table above.

THy4 previewtencent · 2.90% · arena.ai #21
NNemotron 3 Ultranvidia · -8.29% · arena.ai #50
TInklingthinky · -13.61% · arena.ai #52
TInkling Smallthinky · -14.72% · arena.ai #53
USolar Pro 4upstage · -20.18% · arena.ai #54

All 86 model pages

OpenAI 14

Anthropic 12

Google 9

Alibaba 8

Meta 7

DeepSeek 6

Moonshot AI 4

xAI 4

Xiaomi 4

Z.AI 4

Mistral 3

Z AI 2

Tencent 1

Sources & methodology

As of Oct 16, 2026, the arena.ai Agents leaderboard (task success rate) is led by Claude Opus 5.5 (17.18%, Max), followed by GPT-6.1 Sol (14.78%). The LMArena Text leader is Gemini 4 Argon (1,523.9), and Claude Opus 5.5 has the highest Artificial Analysis Intelligence Index (57.6). Among models above the quality bar, MiMo-V2.6-Flash has the lowest official output price ($0.28 per 1M tokens).

arena.ai Agents
Agents leaderboard: task success rate, 95% interval, sessions and rank (arena.ai Agents, via the public Hugging Face dataset lmarena-ai/leaderboard-dataset, CC BY 4.0). Hugging Face
LMArena
Arena score, 95% confidence interval, votes and rank (overall Text leaderboard with style control, the same view arena.ai shows by default; dataset CC BY 4.0).
Artificial Analysis
Intelligence Index, Coding Index, output speed, TTFT / first-answer latency, release dates and official prices (shown on this page only, not in the public API).
OpenRouter
Per-provider prices (the cheapest becomes “lowest route”), context length and listing dates.
Vendor pricing pages
“Input / Output” are official API list prices (USD per 1M tokens); when no official price exists we use the OpenRouter price and mark it with *.

How we compute it

Ranking: by default, the arena.ai Agents task success rate (real users’ coding/tool agent tasks). When a model has several reasoning tiers (Max/High/xHigh), the best-scoring tier is used and labelled; fewer than 10,000 sessions or a 95% half-width above 3 points is marked Preliminary. Models without an agent result follow, ordered by LMArena Text (style control); the Text column is still sortable.
Rank: by default, LMArena Text Arena score with style control (the same view arena.ai shows by default; Bradley-Terry, not Elo). The ± is the half-width of the 95% confidence interval, and neighbouring ranks often overlap. Models with fewer than 5,000 votes or ± above 10 are marked Preliminary. We do not invent a composite score.
Intelligence / Coding Index: Artificial Analysis aggregates of public benchmarks. When a model has several reasoning-effort tiers, the table shows the best tier for the current sort column; switch to “by tier” to see each one.
Prices are USD per 1M tokens. “Lowest route” is the cheapest OpenRouter provider’s input / output price; ⚠ marks routes more than 60% below list (usually promos or a single provider). The best-value board only includes models with Arena ≥ 1400 or Intelligence Index ≥ 40, sorted by official output price.
Latency and speed: TTFT is the time to the first token (including thinking tokens); “Answer” is the time to the first answer token (includes the thinking phase for reasoning models); speed is output tokens per second. All are Artificial Analysis medians.
Updates: Text and other data sync daily at 14:20 (UTC+8), the Agents board at 14:25. Agent rank changes appear only after 14 days of daily records; until then no arrows are shown.
Updates: synced automatically every day at 14:20 (UTC+8). LMArena publishes on its own schedule, so the “Arena published” date can be older than the update date. “This week” compares against the daily archive from 7 days earlier.
Open data: /api/public/llm-leaderboard.php (JSON, LMArena and OpenRouter fields only).

FAQ

What is the best AI model right now?

As of Oct 16, 2026, the arena.ai Agents leaderboard (success rate on real coding/tool tasks) is led by Claude Opus 5.5 (17.18%, 95% interval 13.80%–20.56%), ahead of GPT-6.1 Sol (14.78%). The top intervals overlap heavily, so the exact order is not reliable. On the LMArena Text leaderboard, Gemini 4 Argon leads (1,523.9).

Which good AI model is the cheapest?

Among models above the quality floor (Arena ≥ 1400 or Intelligence Index ≥ 40), MiMo-V2.6-Flash has the lowest official price: $0.14 input / $0.28 output per 1M tokens, followed by MiMo V2.5 ($0.28 output). See the best-value leaderboard.

What is the best open-source (open-weight) AI model?

By Arena score, the top open-weight model is Kimi K3 (Moonshot AI, 1,487.1), followed by MiMo-V2.6-Pro (1,479.2). We track 21 open-weight models with an Arena score — see the open-weight leaderboard. Open weights do not mean unrestricted commercial use; check each licence.

Which AI model is best for coding?

On the Artificial Analysis Coding Index, Claude Fable 5.1 is highest (81.6), followed by Claude Opus 5 (78.0). The index aggregates coding benchmarks and differs from the Arena score; see the full coding leaderboard.

Which AI model is the fastest?

The fastest measured output speed belongs to K2 Horizon 375B A23B (1021 tokens/s); the lowest time to first answer token belongs to K2 Horizon 375B A23B (3.65 s). These are Artificial Analysis medians; for reasoning models the first-answer latency includes thinking time.

Which AI models were released recently?

5 tracked models were released in the last 14 days, including Muse Spark Open (Oct 15, 2026), Muse Wonder (Oct 12, 2026), Muse Wonder Full (Oct 12, 2026), Claude Haiku 5.5 (Oct 7, 2026). New models usually take a few days to appear on LMArena; until then they are listed under “Not yet ranked on Arena”.

How often is the data updated, and where does it come from?

Synced automatically every day: the Agents board comes from arena.ai (public Hugging Face dataset, current release Oct 14, 2026), Text scores from LMArena (released Oct 15, 2026); intelligence and coding indices, speed and latency from Artificial Analysis; route prices and context from OpenRouter. This page was updated Oct 16, 2026.

Why do prices differ from the official site?

Input/output prices are official list prices in USD per million tokens. The lowest route price is the cheapest OpenRouter route, which may be a promotion or a single provider and can differ from local resellers.