MoBang MoBang
ZHEN

Leaderboards

No site-invented aggregate score. The two leaderboards are never merged or converted.

01 / Artificial Analysis

Intelligence Index

Last updated
Data notes

Publisher: Artificial Analysis · Source ↗ · No site-invented aggregate score. The two leaderboards are never merged or converted.

照录 Artificial Analysis 免费端点 /api/v2/language/models/free（tier=free，指数版本 v5）的原样快照：共 726 条模型记录，其中 109 条带 Intelligence Index，按指数降序编号（同分同名次）。指数、中位输出速度、输入/输出价均为官方返回值，本站不改写、不加权、不自创总分。其中 83 条是官方按推理档位分列的同名条目，档位见「档位」列。未收录进本站的模型同样在榜，仅不可点击。

#ModelTierVendor Index / preferenceMedian speedInput / output price
1Gemini 4 Carbon High Google 60 94.4 t/s $4.00 / $20.00
2Claude Opus 5.5 Max Anthropic 59.1 95.1 t/s $4.00 / $20.00
3Gemini 4 Carbon Medium Google 58.3 93.2 t/s $4.00 / $20.00
4Claude Opus 5.5 Xhigh Anthropic 57.4 81.9 t/s $4.00 / $20.00
5GPT-6 Astra Max OpenAI 56.9 50.3 t/s $10.00 / $50.00
6GPT-6 Astra Xhigh OpenAI 55.3 47.4 t/s $10.00 / $50.00
7GPT-6 Astra High OpenAI 54.8 49.3 t/s $10.00 / $50.00
8GPT-6.1 Sol Max OpenAI 54.6 68.7 t/s $2.00 / $10.00
9Claude Sonnet 5.5 Max Anthropic 54.5 136.1 t/s $2.00 / $10.00
10Gemini 4 Carbon Low Google 54.2 83 t/s $4.00 / $20.00
11GPT-6.1 Sol Xhigh OpenAI 52.5 70.8 t/s $2.00 / $10.00
12Claude Opus 5.5 High Anthropic 51.8 77.7 t/s $4.00 / $20.00
13GPT-6 Astra Medium OpenAI 51.6 43.4 t/s $10.00 / $50.00
14GPT-6.1 Terra Max OpenAI 51.3 108.6 t/s $1.00 / $5.00
15Gemini 4 Argon High Google 50.4 91 t/s $4.00 / $20.00
16GPT-6.1 Sol High OpenAI 50.3 63.6 t/s $2.00 / $10.00
17Muse Wonder Full Max Meta 50.1 — —
18Claude Fable 5.1 Xhigh Anthropic 50 61.4 t/s $10.00 / $50.00
19Claude Sonnet 5.5 Xhigh Anthropic 49.9 105.8 t/s $2.00 / $10.00
20Claude Fable 5.1 Max Anthropic 49.2 69.4 t/s $10.00 / $50.00
21Claude Opus 5.5 Medium Anthropic 48.2 76.7 t/s $4.00 / $20.00
22Claude Fable 5.1 High Anthropic 47.2 56.7 t/s $10.00 / $50.00
23Kimi K3.1 Pro — Kimi 46.5 28.6 t/s $2.00 / $10.00
24GPT-6.1 Sol Medium OpenAI 46.3 58.4 t/s $2.00 / $10.00
25GPT-6.1 Terra Xhigh OpenAI 45.3 92 t/s $1.00 / $5.00
26Claude Opus 5 Max Anthropic 44.2 50.6 t/s $5.00 / $25.00
26GPT-6 Sol Max OpenAI 44.2 142.2 t/s $2.00 / $10.00
28Muse Wonder Max Meta 43.6 143.7 t/s $4.00 / $20.00
29GPT-6 Astra Low OpenAI 43.3 42 t/s $10.00 / $50.00
30Claude Fable 5.1 Medium Anthropic 43.2 57 t/s $10.00 / $50.00
31GPT-6.1 Terra High OpenAI 42.4 89.5 t/s $1.00 / $5.00
32Claude Sonnet 5.5 High Anthropic 41.5 108.2 t/s $2.00 / $10.00
33Muse Wonder High Meta 40.5 149.4 t/s $4.00 / $20.00
34Claude Fable 5.1 Low Anthropic 38.7 55.7 t/s $10.00 / $50.00
35GPT-6.1 Terra Medium OpenAI 38.2 89.8 t/s $1.00 / $5.00
36Muse Spark 1.3 Max Meta 36.6 159.2 t/s $1.25 / $4.25
37Claude Haiku 5.5 Max Anthropic 36.5 232.8 t/s $0.10 / $0.50
38Grok 4.7 Xhigh SpaceXAI 35.5 65 t/s $2.00 / $6.00
39Grok 4.7 High SpaceXAI 35.2 73.5 t/s $2.00 / $6.00
40Claude Opus 5.5 Low Anthropic 34.8 77.3 t/s $4.00 / $20.00
40GPT-6.1 Sol Low OpenAI 34.8 59.8 t/s $2.00 / $10.00
42Claude Haiku 5.5 Xhigh Anthropic 34.6 177.9 t/s $0.10 / $0.50
42Tencent Hy4 — Tencent 34.6 93.8 t/s $0.83 / $2.50
44Qwen3.8 Max 0902 Alibaba 33.7 40 t/s $2.00 / $6.00
45DeepSeek V4.1 Flash 1017 Max DeepSeek 32.6 147.7 t/s $0.30 / $1.20
46GPT-5.6 Terra Max OpenAI 32.3 120.7 t/s $2.00 / $12.00
47GLM-5.3 Max Z AI 31.7 81 t/s $1.40 / $4.40
48Grok 4.7 Low SpaceXAI 31.1 54.4 t/s $2.00 / $6.00
49Grok 4.6 Xhigh SpaceXAI 31 72.1 t/s $2.00 / $6.00
50Claude Sonnet 5.5 Medium Anthropic 30.8 103.4 t/s $2.00 / $10.00
50Gemini 3.8 Flash High Google 30.8 122.9 t/s $0.75 / $3.75
52Inkling 2 Small — Thinking Machines 30.6 128.3 t/s $0.30 / $1.00
53GPT-6.1 Terra Non-reasoning OpenAI 30.5 88.5 t/s $1.00 / $5.00
54Gemini 3.8 Flash Medium Google 30.1 126.8 t/s $0.75 / $3.75
55Claude Haiku 5.5 High Anthropic 29.9 174.2 t/s $0.10 / $0.50
55MiMo-V2.6-Pro — Xiaomi 29.9 39.8 t/s $0.43 / $0.87
57Ling 3.1 Flash 1019 — InclusionAI 29.6 — $0.30 / $0.90
58GPT-6.1 Terra Low OpenAI 29.4 89 t/s $1.00 / $5.00
59MiniMax-M3.1-Flash — MiniMax 29.1 166.7 t/s $0.15 / $0.60
60DeepSeek V4.1 Flash 1017 High DeepSeek 28.6 157.2 t/s $0.30 / $1.20
61Step 5 Preview — StepFun 28.5 158.3 t/s $1.00 / $2.70
62GPT-6 Luna Max OpenAI 27.9 123.2 t/s $0.10 / $0.50
63GLM-5.3-Flash — Z AI 27.8 51.3 t/s $0.15 / $0.50
64MiMo-V2.6-Flash — Xiaomi 26.7 48.1 t/s $0.14 / $0.28
65Mistral Large 4 High Mistral 26.1 137 t/s $0.70 / $2.10
66Claude Sonnet 5.5 Low Anthropic 25.6 103.6 t/s $2.00 / $10.00
67Mistral Large 4 Preview — Mistral 25.3 131.6 t/s $0.70 / $2.10
68Muse Spark Open Xhigh Meta 24.9 222.9 t/s $1.25 / $4.25
69Claude Haiku 5.5 Medium Anthropic 24.6 170.5 t/s $0.10 / $0.50
70GPT-5.6 Luna Max OpenAI 23.8 125.5 t/s $0.20 / $1.20
71GPT-6 Luna Xhigh OpenAI 23.5 117.7 t/s $0.10 / $0.50
72DeepSeek V4 Pro 0813 Max DeepSeek 23.1 79.1 t/s $1.32 / $3.96
72GLM-5.3 Low Z AI 23.1 77.3 t/s $1.40 / $4.40
72Mistral Large 4 Medium Mistral 23.1 134.7 t/s $0.70 / $2.10
75Gemini 3.8 Flash Low Google 22.5 128.3 t/s $0.75 / $3.75
76GPT-6 Luna High OpenAI 21.4 120.2 t/s $0.10 / $0.50
77Nanbeige4.3-33B — Nanbeige 20.4 — —
78Qwen3.8 27B Xhigh Alibaba 20.1 38.2 t/s $0.50 / $3.00
79MiniMax-M3 — MiniMax 18.9 136.6 t/s $0.30 / $1.20
80Claude Haiku 5.5 Low Anthropic 18.6 165.9 t/s $0.10 / $0.50
81DeepSeek V4.1 Flash 1017 Non-reasoning DeepSeek 18.5 148.2 t/s $0.30 / $1.20
81GPT-6 Luna Medium OpenAI 18.5 112.1 t/s $0.10 / $0.50
83K2 Horizon 375B A23B — Institute of Foundation Models 17.8 877 t/s $0.00 / $0.00
84Beam 1.0 — Reflection 17.7 367.7 t/s $0.40 / $1.20
85Qwen3.8 27B Medium Alibaba 17.5 38.9 t/s $0.50 / $3.00
86Kimi K3 Low Kimi 17.4 49.5 t/s $3.00 / $15.00
87Qwen3.8 27B Low Alibaba 15.7 39.3 t/s $0.50 / $3.00
88Nemotron 3.5 Super VL — NVIDIA 13.6 279.3 t/s $0.17 / $0.50
89Inkling Small — Thinking Machines 12.9 78.8 t/s $0.30 / $1.20
90DeepSeek V4 Pro 0813 Non-reasoning DeepSeek 12.6 79.6 t/s $1.32 / $3.96
91Inkling Xhigh Thinking Machines 12.5 161.5 t/s $1.00 / $4.05
92Nemotron 3 Ultra 550B A55B Reasoning NVIDIA 11.8 253.8 t/s $0.60 / $2.70
93Gemini 3.5 Flash-Lite — Google 11.7 410 t/s $0.30 / $2.50
94Qwen3.8 27B Non-reasoning Alibaba 10 36 t/s $0.50 / $3.00
95GPT-6 Luna Low OpenAI 9.7 113.7 t/s $0.10 / $0.50
96GPT-6 Luna Non-reasoning OpenAI 9.4 111.1 t/s $0.10 / $0.50
97K-EXAONE 2.0 — LG AI Research 7.6 — —
98Claude 4.5 Haiku Reasoning Anthropic 7.4 95.8 t/s $1.00 / $5.00
99Muse Glimmer High Meta 6.3 108.5 t/s $0.30 / $1.20
100Command A+ — Cohere 6.2 258.1 t/s $0.00 / $0.00
100Gemini 3.1 Flash-Lite — Google 6.2 354.8 t/s $0.25 / $1.50
102Nemotron 3.5 Lightning — NVIDIA 5.5 286.9 t/s $0.06 / $0.20
103Granite 4.2 8B — IBM 5.1 139 t/s $0.06 / $0.25
104Granite 4.2 3B — IBM 4.7 — —
105Mistral Medium 3.5 — Mistral 4.6 170.3 t/s $1.50 / $7.50
106Gemma 4 31B Reasoning Google 4.4 34.9 t/s $0.00 / $0.00
107Mistral Small 4 Reasoning Mistral 4.3 161.2 t/s $0.15 / $0.60
108North Mini Code — Cohere 3.4 174.8 t/s $0.00 / $0.00
109NVIDIA Nemotron 3 Nano 4B — NVIDIA 1.8 — —

Data commentary

# 1 · Gemini 4 Carbon · Index / preference 60 ↗

Models outside our directory are shown as plain names, never fake links.

02 / LMArena

Human preference leaderboard

Last updated
Data notes

Publisher: LMArena · Source ↗ · No site-invented aggregate score. The two leaderboards are never merged or converted.

照录 LMArena 官方公开数据集 lmarena-ai/leaderboard-dataset（CC-BY-4.0）文本总榜 overall 最新一期：共 421 个模型配置，官方发布日 2026-11-09。评分是 Bradley-Terry 模型算出的 Arena 评分（Elo 口径），名次、票数与置信区间均为官方原值，本站不改写、不加权。榜单含未收录进本站的模型，仅不可点击。完整官方数据：https://hf-mirror.com/datasets/lmarena-ai/leaderboard-dataset/resolve/main/text/latest-00000-of-00001.parquet

#ModelVendor Index / preferenceVotes
1Gemini 4 Carbon (High) google1538.3 4,282
2Gemini 4 Argon (High) google1530.2 19,787
3Claude Opus 5.5 (High) anthropic1513 15,249
4Claude Fable 5.1 (Max) anthropic1512.4 20,087
5Claude Opus 5 (Max) anthropic1506.3 35,710
6Muse Wonder (Max) meta1503 12,032
7Claude Opus 5 (High) anthropic1502.3 73,697
8Claude Opus 4.6 (High) anthropic1501.7 84,424
9Gemini 3.8 Flash (High) google1500.4 61,143
10Claude Opus 4.6 anthropic1496.7 89,228
11MiMo-V2.6-Pro xiaomi1491.7 4,066
12Claude Fable 5 (High) anthropic1491.6 45,524
13Muse Spark 1.3 (Max) meta1491.5 26,111
14Claude Opus 4.7 (High) anthropic1489.7 64,308
15Gemini 3.7 Flash (High) google1488.8 33,300
16Qwen3.8-Max alibaba1485.2 36,324
17Muse Spark 1.2 (xHigh) meta1484 15,004
18Claude Opus 4.7 anthropic1483.2 65,369
19Gemini 3.5 Flash (High) google1482.9 47,642
20Gemini 3.1 Pro Preview google1480 132,296
21Gemini 3 Pro google1479.5 41,829
22Gemini 3.6 Flash (High) google1479.3 35,405
23Muse Spark 1.1 meta1478.7 45,562
24Gemini 3.5 Flash (Medium) google1477.9 46,377
25GLM-5.3 (Max) zai1475.9 31,017
26Qwen3.7-Max-Preview alibaba1474.8 3,904
27Kimi K3 (Max) moonshot1474.3 40,867
28Muse Spark meta1474.1 14,009
29GPT-5.5 (High) openai1471.2 68,359
30Qwen3.5-Max-Preview alibaba1470.9 22,419
Showing top 30 of 421 Official dataset ↗

Data commentary

# 1 · Gemini 4 Carbon (High) · Index / preference 1538.3

03 / LMArena

More category boards

More category boards · 21

LMArena publishes 22 category leaderboards; each shows its top 10 below. Preference boards use Arena ratings (Elo), Agent boards use 0–1 task scores — different scales, comparable only within a board.

Publisher: LMArena · CC-BY-4.0 · Official dataset ↗ · Last updated

Text Style Control · 421 entries

Index / preference · 2026-11-09

#ModelIndex / preference
1Gemini 4 Carbon (High) 1526
2Gemini 4 Argon (High) 1522.4
3Muse Wonder (Max) 1511
4Claude Opus 5.5 (High) 1506.1
5Claude Fable 5 (High) 1503.9
6Claude Opus 4.6 (High) 1503
7Claude Fable 5.1 (Max) 1502.7
8Claude Opus 4.7 (High) 1501.1
9Gemini 3.8 Flash (High) 1497.5
10Claude Opus 4.6 1496.5

Text-to-Image · 84 entries

Index / preference · 2026-11-09

#ModelIndex / preference
1GPT-Image-2.5 Sunburst 1428.8
2GPT-Image-2.6 Sunburst (Medium) 1406.1
3GPT-Image-2.5 Flare 1400.2
4GPT-Image-2.6 Flare (Medium) 1382.8
5GPT-Image-2 (Medium) 1381.7
6MAI-Image-2.6 1329.3
7Gemini Nano Banana 2.1 1327.7
8Grok Imagine Image 2.0 1318.6
9Reve 2.1 1301.8
10Grok Imagine Image 2.0 (20260801) 1288

Vision · 167 entries

Index / preference · 2026-11-09

#ModelIndex / preference
1Claude Fable 5 (High) 1325.6
2Claude Opus 5.5 (High) 1323.8
3Claude Fable 5.1 (Max) 1321.6
4Claude Opus 4.7 1318.7
5Claude Opus 5 (High) 1317.5
6Gemini 3.8 Flash (High) 1316.8
7Claude Opus 4.6 (High) 1315.6
8Claude Opus 4.7 (High) 1313.9
9Gemini 3.7 Flash (High) 1313.1
10Claude Opus 4.6 1312.2

Text-to-Video · 50 entries

Index / preference · 2026-11-09

#ModelIndex / preference
1Gemini Omni 1.2 Flash 1540.1
2Gemini Omni 1.1 Flash 1513
3gemini-omni-flash 1509.4
4FLUX 3 Video 1491.1
5Grok Imagine Video 1.5 1487.5
6Dreamina Seedance 2.0 (720p) 1483.4
7Dreamina Seedance 2.5 (720p) 1479.5
8Wan 3.0 1476.2
9SkyReels V4 1458.7
10Muse Video 1457.1

Image Edit · 63 entries

Index / preference · 2026-11-09

#ModelIndex / preference
1GPT-Image-2.5 Sunburst 1519.8
2GPT-Image-2.5 Flare 1484.5
3GPT-Image-2.6 Sunburst (Medium) 1476.7
4MAI-Image-2.7-Preview 1468.3
5GPT-Image-2 (Medium) 1460.9
6GPT-Image-2.6 Flare (Medium) 1460.1
7Grok Imagine Image 2.0 1436.9
8MAI-Image-2.6 1427.7
9Gemini Nano Banana 2.1 1427.2
10Grok Imagine Image 2.0 (20260801) 1418.1

Video Edit · 11 entries

Index / preference · 2026-11-09

#ModelIndex / preference
1Wan 3.0 1424
2Dreamina Seedance 2.5 (720p) 1417.2
3Gemini Omni 1.2 Flash 1395.6
4MiniMax H3 1383
5gemini-omni-flash 1378
6Dreamina Seedance 2.0 (720p) 1369.1
7HappyHorse 1.0 1305.1
8Kling O3 Pro 1262.5
9Grok Imagine Video 1250.1
10Kling O1 Pro 1189.6

WebDev · 154 entries

Index / preference · 2026-11-09

#ModelIndex / preference
1Claude Opus 5.5 (Max) 1817.7
2Claude Sonnet 5.5 (xHigh) 1774.3
3Gemini 4 Carbon (High) 1768
4GPT-6 Astra (Max) 1766.8
5Claude Fable 5.1 (Max) 1744.6
6GPT-6.1 Sol (Max) 1742.8
7Muse Wonder Full (Max) 1723.9
8Claude Sonnet 5.5 (High) 1713.2
9Claude Opus 5 (Max) 1690.8
10Kimi K3.1 Pro (Max) 1687.8

Search · 42 entries

Index / preference · 2026-11-09

#ModelIndex / preference
1Qwen3.8-Max 1259.8
2GPT-5.6 Sol (xHigh) 1257.8
3Claude Opus 4.6 (Search) 1251.7
4GPT-5.5 (Search) 1245.9
5Claude Opus 5 (High) 1239
6Claude Fable 5.1 (High) 1237.3
7GPT-6 Astra (Max) 1230.8
8GPT-6.1 Sol (Max) 1230.4
9Claude Opus 4.7 1230.1
10Claude Fable 5 (High) 1228.2

Document · 46 entries

Index / preference · 2026-11-09

#ModelIndex / preference
1Claude Fable 5.1 (Max) 1514.8
2Claude Opus 5 (High) 1508.7
3Claude Opus 4.6 (High) 1507.6
4Claude Opus 4.6 1506.2
5Claude Fable 5 (High) 1496.6
6Claude Opus 4.7 (High) 1495.7
7Claude Opus 4.7 1494.8
8GPT-5.5 (High) 1484.3
9Gemini 3.8 Flash (High) 1481.9
10Claude Sonnet 4.6 1481.9

Agent · 57 entries

Task score · 2026-11-08

#ModelScore
1Claude Opus 5.5 (Max) 0.200
2Gemini 4 Carbon (High) 0.166
3Claude Sonnet 5.5 (Max) 0.160
4Claude Fable 5.1 (Max) 0.143
5GPT-6 Astra (Max) 0.142
6GPT-6.1 Sol (Max) 0.125
7GPT-6.1 Terra (Max) 0.121
8Gemini 4 Argon (High) 0.108
9Muse Wonder Full (Max) 0.091
10Claude Fable 5 (High) 0.077

Text Factuality · 190 entries

Index / preference · 2026-11-09

#ModelIndex / preference
1Gemini 4 Carbon (High) 1521.2
2Claude Opus 5.5 (High) 1505.5
3Claude Fable 5.1 (Max) 1498.8
4Gemini 4 Argon (High) 1497.8
5Muse Wonder (Max) 1495.1
6Claude Opus 4.6 (High) 1492.6
7Claude Opus 4.6 1488
8Claude Opus 5 (Max) 1487.6
9GPT-5.5 (High) 1485.4
10MiMo-V2.6-Pro 1484.9

Search Style Control · 42 entries

Index / preference · 2026-11-09

#ModelIndex / preference
1GPT-5.6 Sol (xHigh) 1255.4
2GPT-6.1 Sol (Max) 1248.5
3GPT-6 Astra (Max) 1244.8
4GPT-6 Sol (Max) 1229
5Claude Fable 5 (High) 1228.6
6Qwen3.8-Max 1227.2
7Claude Fable 5.1 (High) 1226.8
8GPT-5.5 (Search) 1226
9Claude Opus 4.6 (Search) 1221.7
10Claude Opus 5 (High) 1213.3

Search Factuality · 40 entries

Index / preference · 2026-11-09

#ModelIndex / preference
1GPT-5.6 Sol (xHigh) 1249.5
2GPT-5.5 (Search) 1246.3
3Qwen3.8-Max 1242.9
4GPT-6 Astra (Max) 1238.7
5GPT-6.1 Sol (Max) 1236.5
6Claude Opus 4.6 (Search) 1227.4
7GPT-5.2 (Search) 1224
8Grok 4.5 1220
9Claude Fable 5.1 (High) 1214.4
10ERNIE 5.1 1213.8

Document Style Control · 46 entries

Index / preference · 2026-11-09

#ModelIndex / preference
1Claude Fable 5 (High) 1500.1
2Claude Fable 5.1 (Max) 1498.4
3Claude Opus 4.6 (High) 1496.9
4Claude Opus 4.6 1495.6
5Claude Opus 4.7 1494.4
6Claude Opus 4.7 (High) 1494.3
7GPT-5.6 Sol (xHigh) 1486.5
8Claude Opus 5 (High) 1485.9
9Claude Opus 4.8 (High) 1485.4
10GPT-5.5 (High) 1481.4

Vision Style Control · 167 entries

Index / preference · 2026-11-09

#ModelIndex / preference
1Claude Fable 5 (High) 1309.4
2Claude Opus 4.7 1300.3
3Qwen3.8-Max 1299
4Claude Opus 4.6 (High) 1298.8
5Claude Opus 4.7 (High) 1298.4
6Claude Opus 5.5 (High) 1295.3
7Muse Spark 1294.4
8Gemini 3.7 Flash (High) 1293.8
9Muse Spark 1.2 (xHigh) 1293.5
10Claude Opus 4.6 1293.2

Agent Bash Recovery · 52 entries

Task score · 2026-10-08

#ModelScore
1Claude Sonnet 5.5 (Max) 0.150
2Claude Opus 5 (Max) 0.136
3Claude Opus 5.5 (High) 0.136
4Claude Opus 5 (High) 0.126
5Claude Fable 5.1 (Max) 0.116
6Claude Fable 5 (High) 0.096
7GPT 5.5 (xHigh) 0.095
8Deepseek V4.1 Flash (Max) 0.079
9Claude Sonnet 5 (High) 0.074
10Claude Opus 4.8 (High) 0.072

Agent Bash Reliability · 57 entries

Task score · 2026-11-08

#ModelScore
1Claude Sonnet 5 (High) 0.150
2Claude Opus 5.5 (Max) 0.150
3GPT-6.1 Terra (Max) 0.133
4Claude Sonnet 5.5 (Max) 0.127
5GPT-5.6 Sol (xHigh) 0.113
6GPT-6 Sol (Max) 0.110
7Claude Fable 5 (High) 0.104
8Grok 4.6 (xHigh) 0.102
9Claude Fable 5.1 (Max) 0.100
10Gemini 3.8 Flash (High) 0.099

Agent Praise/Complaint · 57 entries

Task score · 2026-11-08

#ModelScore
1Claude Opus 5.5 (Max) 0.423
2Gemini 4 Carbon (High) 0.395
3Claude Sonnet 5.5 (Max) 0.316
4GPT-6 Astra (Max) 0.309
5Claude Fable 5.1 (Max) 0.298
6GPT-6.1 Sol (Max) 0.284
7Gemini 4 Argon (High) 0.235
8GPT-6.1 Terra (Max) 0.204
9Muse Wonder Full (Max) 0.154
10Claude Fable 5 (High) 0.146

Agent Steerability · 57 entries

Task score · 2026-11-08

#ModelScore
1Gemini 4 Carbon (High) 0.191
2Claude Opus 5.5 (Max) 0.186
3GPT-6.1 Terra (Max) 0.158
4Claude Fable 5.1 (Max) 0.157
5GPT-6 Astra (Max) 0.148
6Claude Sonnet 5.5 (Max) 0.138
7Gemini 4 Argon (High) 0.135
8GPT-6.1 Sol (Max) 0.133
9Muse Wonder Full (Max) 0.104
10GPT-6 Sol (Max) 0.101

Agent Tool Hallucination · 57 entries

Task score · 2026-11-08

#ModelScore
1GLM-5.3-Flash 0.009
2GPT-6 Astra (Max) 0.009
3GPT-6.1 Sol (Max) 0.009
4Kimi K3.1 Pro (Max) 0.009
5GPT-6.1 Terra (Max) 0.009
6GPT-6 Luna (Low) 0.009
7GPT-6 Luna (Medium) 0.009
8Grok 4.6 (xHigh) 0.009
9GPT-5.6 Sol (xHigh) 0.009
10GLM-5.3 (Max) 0.009

Agent Task Outcome · 57 entries

Task score · 2026-11-08

#ModelScore
1Claude Opus 5.5 (Max) 0.207
2Claude Sonnet 5.5 (Max) 0.195
3Gemini 4 Carbon (High) 0.184
4Gemini 4 Argon (High) 0.141
5GPT-6 Astra (Max) 0.136
6Claude Fable 5.1 (Max) 0.131
7GPT-6.1 Sol (Max) 0.112
8Muse Wonder Full (Max) 0.110
9GPT-6.1 Terra (Max) 0.106
10Claude Opus 5 (Max) 0.105
0 / 3 Compare Open comparison →