Enter opens the highlighted result. Esc closes.

LMArena Text: coding leaderboard

Gemini 4 Argon leads
1546
models measured
156
lead over #2
+1 Elo
median
1438

Leader on LMArena Text: coding · read October 22

lmarena_text_coding.py


        # LMArena Text: coding, read October 22
        leaders = {
            "Gemini 4 Argon": 1546,    "Claude Opus 5.5": 1545,    "Claude Opus 4.6": 1534,
        }

On October 22, 2026, 168 of our catalog's models had a LMArena Text: coding result, and Google Gemini 4 Argon led with 1546, ahead of Anthropic Claude Opus 5.5 at 1545.

Text prompts about code. People ask a question, compare two anonymous answers and vote for the better one; the rating is built from those votes, as LMArena publishes it.

Role in the index

A coding board we show beside the Vibe Coding Index, not inside it: the index keeps the six boards it was defined on, so a score does not move every time a board is added. Read the methodology

168 models with a result

Original board: LMArena (Hugging Face dataset)
LMArena Text: coding results for models in the catalog
# Model Result VotesInterval (±) Evidence Coding index Output $/Mtok
1 Gemini 4 ArgonGoogle 1546 1,236±17.0 81.0 $10.00
2 Claude Opus 5.5Anthropic 1545 2,143±13.2 88.8 $20.00
3 Claude Opus 4.6Anthropic 1534 24,104±5.1 57.2 $25.00
4 Claude Opus 5Anthropic 1533 8,413±7.4 83.0 $25.00
5 MiMo-V2.6-ProXiaomi 1533 1,102±17.6 65.4 $0.87
6 Claude Fable 5.1Anthropic 1532 3,112±11.0 84.2 $50.00
7 Muse WonderMeta 1522 1,234±16.9 71.9 $20.00
8 Claude Opus 4.7Anthropic 1519 18,580±5.8 67.5 $25.00
9 Claude Fable 5Anthropic 1518 11,128±6.5 79.3 $50.00
10 Claude Sonnet 5.5Anthropic 1513 1,914±13.8 87.3 $10.00
11 Muse Spark 1.3Meta 1510 4,958±8.9 57.4 $4.25
12 Gemini 3.8 FlashGoogle 1508 10,731±6.9 61.6 $3.75
13 Kimi K3Moonshot AI 1508 8,643±7.1 62.3 $15.00
14 GLM 5.3 FlashZ.ai 1507 9,192±7.2 57.7 $0.50
15 Muse Spark 1.2Meta 1505 2,474±12.3 55.7 $4.25
16 Claude Opus 4.5Anthropic 1503 7,787±7.2 44.0 $25.00
17 Claude Sonnet 4.6Anthropic 1503 19,732±5.5 57.3 $15.00
18 DeepSeek V4.1 FlashDeepSeek 1502 3,680±10.0 62.5 $0.84
19 Qwen3.8 Max (0902)Qwen 1502 8,078±7.4 62.4 $6.00
20 MiMo-V2.5-ProXiaomi 1501 20,773±5.4 31.6 $0.9152
21 MiMo-V2.6-FlashXiaomi 1499 3,010±11.2 54.7 $0.28
22 Gemini 3.7 FlashGoogle 1499 7,905±7.5 58.0 $3.75
23 Muse Spark 1.1Meta 1498 12,370±6.3 70.3 $4.25
24 GLM 5.3Z.ai 1497 5,699±8.4 70.6 $4.40
25 GPT-5.4OpenAI 1496 17,594±5.8 64.4 $15.00
26 GPT-5.6 SolOpenAI 1496 11,144±6.6 73.5 $20.00
27 GPT-5.5OpenAI 1494 19,152±5.7 71.3 $30.00
28 Gemini 3.5 FlashGoogle 1493 13,845±6.0 39.8 $9.00
29 Gemini 3.6 FlashGoogle 1491 10,360±6.8 62.5 $3.75
30 Claude Opus 4.8Anthropic 1490 17,413±5.8 65.0 $25.00
31 GPT-6 AstraOpenAI 1489 2,977±11.2 85.1 $50.00
32 Kimi K2.6Moonshot AI 1489 11,093±6.8 52.1 $4.00
33 Claude Sonnet 4.5Anthropic 1488 19,940±4.8 39.5 $15.00
34 GLM 5.2Z.ai 1487 13,716±6.1 61.1 $4.40
35 GLM 5.1Z.ai 1485 17,433±5.4 49.2 $4.40
36 GPT-5.6 TerraOpenAI 1485 11,966±6.4 63.9 $12.00
37 Step 5 PreviewStepFun 1485 2,074±12.9 61.1 $2.70
38 Gemini 3.1 Pro PreviewGoogle 1484 35,474±4.5 32.3 $12.00
39 Kimi K2.5Moonshot AI 1483 1,871±13.4 38.6 $2.85
40 Qwen3.8 27BQwen 1483 6,853±7.8 74.2 $2.55
41 Claude Sonnet 5Anthropic 1483 13,564±6.1 57.7 $10.00
42 Claude Opus 4.1Anthropic 1479 9,923±6.4 Not benchmarked $75.00
43 Mistral Large 4Mistral AI 1478 2,115±12.9 56.4 $4.18
44 GPT-6.1 SolOpenAI 1478 1,462±15.8 82.4 $10.00
45 Grok 4.5xAI 1474 11,105±6.6 58.6 $6.00
46 Qwen3.7 PlusQwen 1473 12,169±6.4 33.2 $1.28
47 R Beam 1.0 501B A23BReflection 1473 1,019±17.9 Not benchmarked $1.10
48 MiniMax M3MiniMax 1470 18,701±5.6 39.2 $1.20
49 DeepSeek V4 Pro 0423DeepSeek 1470 17,137±5.9 38.7 $2.976
50 DeepSeek V4 Pro 0813DeepSeek 1469 2,804±11.3 56.1 $1.98
51 MiMo-V2.5Xiaomi 1469 13,645±6.5 50.0 $0.336
52 Nemotron 3 UltraNVIDIA 1468 3,187±10.9 30.0 $2.40
53 Qwen3.6 PlusQwen 1467 14,675±6.2 44.1 $1.95
54 GPT-5.6 LunaOpenAI 1466 11,119±6.6 58.0 $1.20
55 GLM 5V TurboZ.ai 1466 2,941±11.1 Not benchmarked $4.00
56 Hy3Tencent 1466 3,471±10.2 Not benchmarked $0.528
57 Grok 4.6xAI 1466 7,668±7.5 65.7 $6.00
58 T InklingThinking Machines 1466 11,531±6.5 31.5 $4.05
59 Qwen3.5 397B A17BQwen 1464 26,863±4.7 Not benchmarked $2.34
60 GLM 5Z.ai 1461 7,628±7.2 41.7 $3.20
61 Mistral Medium 3.5Mistral AI 1460 3,294±10.7 25.5 $7.50
62 Gemma 4 31BGoogle 1459 1,417±15.0 39.0 $0.40
63 DeepSeek V4 Flash 0423DeepSeek 1457 15,284±6.2 Not benchmarked $0.28
64 GLM 4.7Z.ai 1454 2,480±11.7 55.1 $2.20
65 MiniMax M2.7MiniMax 1454 24,504±5.0 36.2 $1.20
66 Claude Haiku 4.5Anthropic 1454 38,877±4.0 35.6 $5.00
67 GPT-5.1OpenAI 1453 8,409±6.9 40.4 $10.00
68 DeepSeek V3.2DeepSeek 1453 8,880±6.6 30.0 $0.88
69 Gemini 3.5 Flash LiteGoogle 1453 9,921±6.9 49.0 $2.50
70 Gemini 2.5 ProGoogle 1452 26,942±4.2 19.1 $10.00
71 T Inkling SmallThinking Machines 1450 9,277±7.0 27.3 $1.20
72 GLM 4.6Z.ai 1449 7,598±7.1 8.8 $2.20
73 GPT-6 SolOpenAI 1448 3,167±11.1 76.0 $10.00
74 Gemma 4 26B A4BGoogle 1446 1,444±14.7 Not benchmarked $0.60
75 GPT-5.2OpenAI 1442 12,238±6.0 55.9 $14.00
76 Qwen3 Next 80B A3B InstructQwen 1440 4,816±8.6 Not benchmarked $1.10
77 DeepSeek V3.2 ExpDeepSeek 1438 1,930±13.3 Not benchmarked $0.41
78 GPT-5.4 MiniOpenAI 1438 17,241±5.8 35.8 $4.50
79 Qwen3 VL 235B A22B InstructQwen 1438 2,309±12.9 Not benchmarked $1.90
80 Solar Pro 4Upstage 1438 5,940±8.3 Not benchmarked $0.60
81 GPT-6 LunaOpenAI 1437 14,401±6.3 57.3 $0.50
82 GPT-5OpenAI 1436 6,398±7.9 38.8 $10.00
83 Step 3.5 FlashStepFun 1436 15,185±5.7 Not benchmarked $0.30
84 Qwen3.5-122B-A10BQwen 1436 8,187±7.0 Not benchmarked $2.08
85 GLM 4.5Z.ai 1434 4,741±8.8 Not benchmarked $2.20
86 Mistral Medium 3.1Mistral AI 1433 21,549±4.5 Not benchmarked $2.00
87 Grok 4.7xAI 1432 2,956±11.4 66.7 $6.00
88 R1 0528DeepSeek 1427 2,690±11.4 Not benchmarked $2.18
89 Qwen3.5-27BQwen 1427 7,936±7.1 Not benchmarked $1.56
90 DeepSeek V3.1 TerminusDeepSeek 1425 633±23.3 Not benchmarked $1.0142
91 Qwen3 235B A22B Thinking 2507Qwen 1424 1,590±14.7 Not benchmarked $3.50
92 Gemini 2.5 FlashGoogle 1423 26,365±4.2 Not benchmarked $2.50
93 Hy3 previewTencent 1421 2,056±13.4 Not benchmarked $0.60
94 Qwen3 30B A3B Instruct 2507Qwen 1416 4,615±8.8 Not benchmarked $0.30
95 Grok 4.3xAI 1415 19,938±5.6 37.4 $2.50
96 Qwen3 Coder 480B A35BQwen 1412 4,806±9.0 Not benchmarked $1.50
97 Qwen3.5-FlashQwen 1412 17,723±5.6 41.1 $0.26
98 Qwen3.5-35B-A3BQwen 1410 8,392±7.0 Not benchmarked $1.30
99 o3OpenAI 1407 11,584±6.2 Not benchmarked $8.00
100 GPT-5 MiniOpenAI 1406 5,516±8.3 34.2 $2.00
101 GPT-5.4 NanoOpenAI 1404 17,655±5.9 44.8 $1.25
102 Nemotron 3 SuperNVIDIA 1403 1,882±13.2 Not benchmarked $0.45
103 Claude Opus 4RetiredAnthropic 1401 7,830±7.2 Not benchmarked $75.00
104 Gemini 3.1 Flash Lite PreviewGoogle 1400 17,848±5.7 22.7 $1.50
105 GLM 4.5 AirZ.ai 1397 6,101±7.7 Not benchmarked $1.10
106 Qwen3 Next 80B A3B ThinkingQwen 1392 2,668±11.4 Not benchmarked $1.20
107 GPT-4.1OpenAI 1390 9,239±6.6 Not benchmarked $8.00
108 Mercury 2Inception 1390 801±20.1 Not benchmarked $0.75
109 GLM 4.6VZ.ai 1389 543±24.6 Not benchmarked $0.90
110 Mistral Medium 3Mistral AI 1385 5,844±8.0 Not benchmarked $2.00
111 Nova 2 LiteAmazon 1385 2,581±11.5 Not benchmarked $2.50
112 GLM 4.7 FlashZ.ai 1382 2,794±10.9 Not benchmarked $0.40
113 MiniMax M2.5MiniMax 1380 11,341±6.4 37.2 $1.20
114 gpt-oss-120bOpenAI 1379 6,410±7.7 Not benchmarked $0.50
115 Granite 4.2 8BIBM Granite 1378 829±21.2 Not benchmarked $0.20
116 Nemotron 3 Nano 30B A3BNVIDIA 1378 3,330±10.2 Not benchmarked $0.22
117 o3 MiniOpenAI 1378 2,596±11.6 Not benchmarked $4.40
118 R1RetiredDeepSeek 1371 2,317±11.8 Not benchmarked $2.50
119 MiniMax M2MiniMax 1371 1,550±15.0 Not benchmarked $1.02
120 o4 MiniOpenAI 1368 8,649±6.8 Not benchmarked $4.40
121 GPT-4.1 MiniOpenAI 1367 6,820±7.5 Not benchmarked $1.60
122 o1OpenAI 1367 3,973±9.6 Not benchmarked $60.00
123 o1-miniRetiredOpenAI 1362 8,478±7.3 Not benchmarked $4.40
124 MiniMax M1MiniMax 1359 6,399±7.6 Not benchmarked $2.20
125 Qwen3 32BQwen 1357 513±24.1 Not benchmarked $0.40
126 Trinity Large ThinkingArcee AI 1357 8,550±7.4 Not benchmarked $0.80
127 GPT-5 NanoOpenAI 1351 1,665±14.6 Not benchmarked $0.40
128 Gemini 2.0 FlashRetiredGoogle 1350 6,961±7.2 Not benchmarked $0.40
129 GLM 4.5VZ.ai 1347 964±18.6 Not benchmarked $1.80
130 Claude 3.5 SonnetRetiredAnthropic 1342 14,908±5.5 Not benchmarked $15.00
131 Claude 3.7 SonnetRetiredAnthropic 1339 7,075±7.4 Not benchmarked $15.00
132 Qwen3 30B A3BQwen 1337 4,505±8.8 Not benchmarked $0.50
133 Command ACohere 1330 10,237±6.2 Not benchmarked $10.00
134 Qwen-PlusQwen 1328 893±18.2 Not benchmarked $0.78
135 Gemma 3 27BGoogle 1322 8,024±6.8 Not benchmarked $0.30
136 Mistral Small 3.1 24BMistral AI 1309 6,111±7.9 Not benchmarked $0.555
137 gpt-oss-20bOpenAI 1307 2,112±13.1 Not benchmarked $0.15
138 GPT-4.1 NanoOpenAI 1306 807±19.3 Not benchmarked $0.40
139 Llama 4 MaverickMeta Llama 1301 6,939±7.5 Not benchmarked $1.00
140 GPT-4o (2024-05-13)OpenAI 1297 19,526±6.4 Not benchmarked $15.00
141 Gemini 1.5 ProRetiredGoogle 1294 9,175±6.8 Not benchmarked $5.00
142 Qwen2.5 72B InstructQwen 1292 6,688±7.6 Not benchmarked $0.40
143 GPT-4o-mini (2024-07-18)OpenAI 1290 10,928±6.5 Not benchmarked $0.60
144 Claude 3.5 HaikuRetiredAnthropic 1286 11,145±6.0 Not benchmarked $4.00
145 Llama 4 ScoutMeta Llama 1286 5,228±8.5 Not benchmarked $0.50
146 GPT-4o (2024-08-06)OpenAI 1283 7,318±7.9 Not benchmarked $10.00
147 Gemma 3 12BGoogle 1281 543±22.8 Not benchmarked $0.1625
148 Qwen2.5 Coder 32B InstructQwen 1276 873±18.1 Not benchmarked $1.00
149 Mistral LargeMistral AI 1275 4,212±8.8 Not benchmarked $6.00
150 Nova Pro 1.0Amazon 1270 3,853±9.1 Not benchmarked $3.20
151 GPT-4 TurboOpenAI 1268 17,104±7.1 Not benchmarked $30.00
152 Llama 3.3 70B InstructMeta Llama 1268 8,735±6.5 Not benchmarked $0.72
153 Claude 3 OpusRetiredAnthropic 1264 33,748±5.8 Not benchmarked $75.00
154 Gemini 1.5 FlashRetiredGoogle 1261 5,892±8.0 Not benchmarked $0.30
155 Llama 3.1 70B InstructMeta Llama 1260 9,389±7.1 Not benchmarked $0.56
156 Mistral Small 3Mistral AI 1246 2,083±12.5 Not benchmarked $0.08
157 Nova Lite 1.0Amazon 1239 3,060±10.3 Not benchmarked $0.24
158 Phi 4Microsoft 1231 3,305±9.8 Not benchmarked $0.14
159 Gemma 3 4BGoogle 1230 605±23.4 Not benchmarked $0.075
160 Claude 3 SonnetRetiredAnthropic 1223 18,888±7.3 Not benchmarked $15.00
161 Nova Micro 1.0Amazon 1218 2,981±10.3 Not benchmarked $0.14
162 Gemma 2 27BGoogle 1211 12,088±6.3 Not benchmarked $0.65
163 GPT-4OpenAI 1209 8,306±9.3 Not benchmarked $60.00
164 Claude 3 HaikuRetiredAnthropic 1199 20,898±6.8 Not benchmarked $1.25
165 Llama 3.1 8B InstructMeta Llama 1195 8,582±7.4 Not benchmarked $0.08
166 Command R (08-2024)Cohere 1187 1,675±13.8 Not benchmarked $0.60
167 Llama 3.2 3B InstructMeta Llama 1098 1,351±15.8 Not benchmarked $0.3325
168 Llama 3.2 1B InstructMeta Llama 1070 1,346±15.8 Not benchmarked $0.201

Only models in our catalog are listed, and each appears once with its best published run. 184 rows were read from the source on October 22, 2026, and rows that match no catalog model are left out. Every other column is a figure the board publishes for the same run.