Enter opens the highlighted result. Esc closes.

LMArena Text: software and IT leaderboard

Gemini 4 Argon leads
1556
models measured
156
lead over #2
+17 Elo
median
1436

Leader on LMArena Text: software and IT · read October 21

lmarena_text_software_and_it.py


        # LMArena Text: software and IT, read October 21
        leaders = {
            "Gemini 4 Argon": 1556,    "Claude Opus 5.5": 1538,    "Claude Fable 5.1": 1530,
        }

On October 21, 2026, 168 of our catalog's models had a LMArena Text: software and IT result, and Google Gemini 4 Argon led with 1556, ahead of Anthropic Claude Opus 5.5 at 1538.

Prompts from software and IT services work. 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: software and IT results for models in the catalog
# Model Result VotesInterval (±) Evidence Coding index Output $/Mtok
1 Gemini 4 ArgonGoogle 1556 1,826±14.1 81.0 $10.00
2 Claude Opus 5.5Anthropic 1538 3,282±10.8 88.8 $20.00
3 Claude Fable 5.1Anthropic 1530 5,159±8.8 84.2 $50.00
4 MiMo-V2.6-ProXiaomi 1528 1,642±14.3 65.4 $0.87
5 Claude Opus 4.6Anthropic 1527 33,986±4.5 57.2 $25.00
6 Claude Opus 5Anthropic 1527 12,221±6.4 83.0 $25.00
7 Claude Opus 4.7Anthropic 1516 26,191±5.1 67.5 $25.00
8 Muse WonderMeta 1515 1,825±14.0 71.9 $20.00
9 Claude Fable 5Anthropic 1513 16,098±5.7 79.3 $50.00
10 Muse Spark 1.3Meta 1511 7,167±7.7 57.4 $4.25
11 Gemini 3.8 FlashGoogle 1507 15,501±6.1 61.6 $3.75
12 Muse Spark 1.2Meta 1505 3,594±10.3 55.7 $4.25
13 Claude Sonnet 5.5Anthropic 1504 2,790±11.5 87.3 $10.00
14 GLM 5.3 FlashZ.ai 1500 13,518±6.3 57.7 $0.50
15 Kimi K3Moonshot AI 1499 13,023±6.1 62.3 $15.00
16 Gemini 3.7 FlashGoogle 1498 11,128±6.5 58.0 $3.75
17 Qwen3.8 Max (0902)Qwen 1498 11,606±6.4 62.4 $6.00
18 Muse Spark 1.1Meta 1498 17,321±5.6 70.3 $4.25
19 MiMo-V2.6-FlashXiaomi 1497 4,725±9.0 54.7 $0.28
20 DeepSeek V4.1 FlashDeepSeek 1496 5,270±8.5 62.5 $0.78
21 MiMo-V2.5-ProXiaomi 1495 30,284±4.7 31.6 $0.9152
22 Gemini 3.5 FlashGoogle 1494 19,409±5.3 39.8 $9.00
23 GLM 5.3Z.ai 1493 8,761±7.1 70.6 $4.40
24 GPT-5.5OpenAI 1493 27,452±5.0 71.3 $30.00
25 Gemini 3.6 FlashGoogle 1492 14,505±6.0 62.5 $3.75
26 Claude Sonnet 4.6Anthropic 1491 27,752±4.9 57.3 $15.00
27 GPT-5.4OpenAI 1491 25,463±5.1 64.4 $15.00
28 GPT-5.6 SolOpenAI 1489 16,174±5.8 73.5 $20.00
29 Claude Opus 4.8Anthropic 1488 25,111±5.2 65.0 $25.00
30 Gemini 3.1 Pro PreviewGoogle 1487 50,815±4.0 32.3 $12.00
31 GLM 5.2Z.ai 1486 19,889±5.4 61.1 $4.40
32 Kimi K2.6Moonshot AI 1484 16,041±5.9 52.1 $4.00
33 GLM 5.1Z.ai 1484 25,190±4.7 49.2 $4.40
34 Claude Opus 4.5Anthropic 1483 26,880±4.6 44.0 $25.00
35 GPT-5.6 TerraOpenAI 1482 17,397±5.6 63.9 $12.00
36 Qwen3.8 27BQwen 1478 9,805±6.8 74.2 $2.55
37 GPT-6.1 SolOpenAI 1476 2,475±12.3 82.4 $10.00
38 GPT-6 AstraOpenAI 1474 4,750±9.0 85.1 $50.00
39 Claude Sonnet 5Anthropic 1474 19,596±5.4 57.7 $10.00
40 Step 5 PreviewStepFun 1473 3,192±10.6 61.1 $2.70
41 Qwen3.7 PlusQwen 1473 17,130±5.7 33.2 $1.28
42 Claude Sonnet 4.5Anthropic 1473 30,313±4.2 39.5 $15.00
43 Grok 4.5xAI 1471 15,963±5.8 58.6 $6.00
44 Kimi K2.5Moonshot AI 1471 2,884±10.7 38.6 $2.85
45 DeepSeek V4 Pro 0423DeepSeek 1469 23,641±5.2 38.7 $2.716
46 Nemotron 3 UltraNVIDIA 1468 4,421±9.4 30.0 $2.40
47 Mistral Large 4Mistral AI 1467 3,255±10.4 56.4 $4.18
48 MiniMax M3MiniMax 1466 26,455±5.0 39.2 $1.20
49 T InklingThinking Machines 1465 16,482±5.7 31.5 $4.05
50 GPT-5.6 LunaOpenAI 1463 15,925±5.8 58.0 $1.20
51 Gemma 4 31BGoogle 1463 2,223±12.0 39.0 $0.40
52 MiMo-V2.5Xiaomi 1463 19,291±5.7 50.0 $0.336
53 Qwen3.5 397B A17BQwen 1463 37,889±4.2 Not benchmarked $2.34
54 Hy3Tencent 1463 5,048±8.6 Not benchmarked $0.33
55 DeepSeek V4 Pro 0813DeepSeek 1462 4,090±9.4 56.1 $1.98
56 Qwen3.6 PlusQwen 1462 20,148±5.5 44.1 $1.95
57 R Beam 1.0 501B A23BReflection 1461 1,460±15.1 Not benchmarked $1.10
58 GLM 5Z.ai 1460 11,154±6.1 41.7 $3.20
59 GLM 5V TurboZ.ai 1460 4,160±9.3 Not benchmarked $4.00
60 Gemini 2.5 ProGoogle 1459 44,025±3.5 19.1 $10.00
61 Mistral Medium 3.5Mistral AI 1458 4,593±9.2 25.5 $7.50
62 Grok 4.6xAI 1457 11,522±6.4 65.7 $6.00
63 Claude Opus 4.1Anthropic 1456 16,737±5.2 Not benchmarked $75.00
64 GLM 4.6Z.ai 1455 12,605±5.8 8.8 $2.20
65 GPT-5.1OpenAI 1454 14,119±5.7 40.4 $10.00
66 Gemma 4 26B A4BGoogle 1454 2,212±11.9 Not benchmarked $0.60
67 GLM 4.7Z.ai 1453 4,119±9.3 55.1 $2.20
68 DeepSeek V4 Flash 0423DeepSeek 1453 21,372±5.5 Not benchmarked $0.28
69 Gemini 3.5 Flash LiteGoogle 1451 14,371±6.0 49.0 $2.50
70 DeepSeek V3.2DeepSeek 1449 14,296±5.5 30.0 $0.88
71 T Inkling SmallThinking Machines 1447 13,196±6.1 27.3 $1.20
72 Qwen3 Next 80B A3B InstructQwen 1447 8,051±6.9 Not benchmarked $1.10
73 MiniMax M2.7MiniMax 1446 34,808±4.4 36.2 $1.20
74 Qwen3 VL 235B A22B InstructQwen 1442 4,003±10.1 Not benchmarked $1.90
75 GLM 4.5Z.ai 1440 8,090±7.1 Not benchmarked $2.20
76 Claude Haiku 4.5Anthropic 1439 56,889±3.5 35.6 $5.00
77 DeepSeek V3.2 ExpDeepSeek 1438 3,202±10.3 Not benchmarked $0.41
78 Mistral Medium 3.1Mistral AI 1436 33,909±3.8 Not benchmarked $2.00
79 Qwen3.5-122B-A10BQwen 1436 11,704±6.1 Not benchmarked $2.08
80 GPT-5.4 MiniOpenAI 1436 25,032±5.2 35.8 $4.50
81 R1 0528DeepSeek 1435 5,531±8.3 Not benchmarked $2.18
82 Step 3.5 FlashStepFun 1434 22,762±4.9 Not benchmarked $0.30
83 GPT-5.2OpenAI 1434 18,414±5.1 55.9 $14.00
84 GPT-6 SolOpenAI 1433 4,975±9.0 76.0 $10.00
85 Qwen3.5-27BQwen 1431 11,356±6.1 Not benchmarked $1.56
86 Qwen3 235B A22B Thinking 2507Qwen 1431 2,910±10.9 Not benchmarked $3.50
87 Solar Pro 4Upstage 1431 8,785±7.0 Not benchmarked $0.60
88 DeepSeek V3.1 TerminusDeepSeek 1426 1,132±17.5 Not benchmarked $1.0142
89 Gemini 2.5 FlashGoogle 1425 43,842±3.5 Not benchmarked $2.50
90 Hy3 previewTencent 1423 2,801±11.4 Not benchmarked $0.60
91 GPT-6 LunaOpenAI 1423 22,318±5.7 57.3 $0.50
92 Grok 4.7xAI 1421 4,708±9.2 66.7 $6.00
93 GPT-5OpenAI 1420 10,821±6.4 38.8 $10.00
94 Qwen3 30B A3B Instruct 2507Qwen 1417 7,960±7.1 Not benchmarked $0.30
95 Qwen3.5-FlashQwen 1416 25,038±5.0 41.1 $0.26
96 Grok 4.3xAI 1416 28,521±5.0 37.4 $2.50
97 Qwen3.5-35B-A3BQwen 1415 12,054±6.0 Not benchmarked $1.30
98 o3OpenAI 1415 19,147±5.2 Not benchmarked $8.00
99 Gemini 3.1 Flash Lite PreviewGoogle 1413 25,395±5.1 22.7 $1.50
100 Nemotron 3 SuperNVIDIA 1409 2,832±10.8 Not benchmarked $0.45
101 GPT-5.4 NanoOpenAI 1402 24,952±5.2 44.8 $1.25
102 GLM 4.5 AirZ.ai 1401 10,461±6.2 Not benchmarked $1.10
103 Nova 2 LiteAmazon 1394 4,306±9.1 Not benchmarked $2.50
104 GPT-5 MiniOpenAI 1394 8,919±6.8 34.2 $2.00
105 Qwen3 Next 80B A3B ThinkingQwen 1393 4,739±8.7 Not benchmarked $1.20
106 Qwen3 Coder 480B A35BQwen 1393 8,457±7.2 Not benchmarked $1.50
107 GPT-4.1OpenAI 1391 16,435±5.4 Not benchmarked $8.00
108 GLM 4.6VZ.ai 1391 935±19.0 Not benchmarked $0.90
109 GLM 4.7 FlashZ.ai 1389 4,288±8.8 Not benchmarked $0.40
110 gpt-oss-120bOpenAI 1387 10,218±6.4 Not benchmarked $0.50
111 Mistral Medium 3Mistral AI 1385 10,553±6.5 Not benchmarked $2.00
112 Mercury 2Inception 1385 1,112±17.2 Not benchmarked $0.75
113 MiniMax M2.5MiniMax 1383 16,481±5.6 37.2 $1.20
114 Nemotron 3 Nano 30B A3BNVIDIA 1383 5,236±8.4 Not benchmarked $0.22
115 Claude Opus 4RetiredAnthropic 1381 14,219±6.0 Not benchmarked $75.00
116 R1RetiredDeepSeek 1375 3,954±9.1 Not benchmarked $2.50
117 MiniMax M2MiniMax 1373 2,458±11.9 Not benchmarked $1.02
118 o4 MiniOpenAI 1367 14,691±5.7 Not benchmarked $4.40
119 Granite 4.2 8BIBM Granite 1367 1,164±17.9 Not benchmarked $0.20
120 o1OpenAI 1366 6,584±7.7 Not benchmarked $60.00
121 Qwen3 32BQwen 1366 843±19.0 Not benchmarked $0.40
122 o3 MiniOpenAI 1364 4,338±9.3 Not benchmarked $4.40
123 Trinity Large ThinkingArcee AI 1362 12,290±6.4 Not benchmarked $0.80
124 Gemini 2.0 FlashRetiredGoogle 1361 12,123±5.8 Not benchmarked $0.40
125 GPT-4.1 MiniOpenAI 1360 12,393±6.1 Not benchmarked $1.60
126 MiniMax M1MiniMax 1359 11,210±6.1 Not benchmarked $2.20
127 Gemma 3 27BGoogle 1354 14,082±5.5 Not benchmarked $0.30
128 o1-miniRetiredOpenAI 1354 13,214±6.2 Not benchmarked $4.40
129 GLM 4.5VZ.ai 1353 1,693±14.0 Not benchmarked $1.80
130 GPT-5 NanoOpenAI 1345 2,811±11.2 Not benchmarked $0.40
131 Qwen-PlusQwen 1343 1,419±15.0 Not benchmarked $0.78
132 Qwen3 30B A3BQwen 1340 8,149±6.9 Not benchmarked $0.50
133 Command ACohere 1336 17,976±5.1 Not benchmarked $10.00
134 Claude 3.5 SonnetRetiredAnthropic 1316 24,999±4.6 Not benchmarked $15.00
135 Claude 3.7 SonnetRetiredAnthropic 1314 12,738±6.0 Not benchmarked $15.00
136 Gemma 3 12BGoogle 1313 867±18.7 Not benchmarked $0.1625
137 gpt-oss-20bOpenAI 1311 3,591±10.1 Not benchmarked $0.15
138 GPT-4.1 NanoOpenAI 1305 1,454±14.7 Not benchmarked $0.40
139 Gemini 1.5 ProRetiredGoogle 1304 14,433±5.8 Not benchmarked $5.00
140 Mistral Small 3.1 24BMistral AI 1301 10,900±6.4 Not benchmarked $0.555
141 Llama 4 MaverickMeta Llama 1299 12,286±6.1 Not benchmarked $1.00
142 GPT-4o (2024-05-13)OpenAI 1297 31,401±5.6 Not benchmarked $15.00
143 Qwen2.5 72B InstructQwen 1292 10,448±6.6 Not benchmarked $0.40
144 GPT-4o-mini (2024-07-18)OpenAI 1291 17,795±5.5 Not benchmarked $0.60
145 Llama 4 ScoutMeta Llama 1286 9,503±6.8 Not benchmarked $0.50
146 Gemini 1.5 FlashRetiredGoogle 1278 9,225±6.8 Not benchmarked $0.30
147 GPT-4o (2024-08-06)OpenAI 1278 11,864±6.7 Not benchmarked $10.00
148 Mistral LargeMistral AI 1274 6,815±7.3 Not benchmarked $6.00
149 Llama 3.3 70B InstructMeta Llama 1273 14,852±5.3 Not benchmarked $0.72
150 Claude 3.5 HaikuRetiredAnthropic 1272 19,603±4.9 Not benchmarked $4.00
151 Nova Pro 1.0Amazon 1271 6,163±7.5 Not benchmarked $3.20
152 Gemma 3 4BGoogle 1269 986±18.4 Not benchmarked $0.075
153 GPT-4 TurboOpenAI 1267 27,573±6.1 Not benchmarked $30.00
154 Qwen2.5 Coder 32B InstructQwen 1261 1,381±14.7 Not benchmarked $1.00
155 Llama 3.1 70B InstructMeta Llama 1260 14,811±6.1 Not benchmarked $0.56
156 Claude 3 OpusRetiredAnthropic 1259 54,971±5.0 Not benchmarked $75.00
157 Mistral Small 3Mistral AI 1248 3,478±9.9 Not benchmarked $0.08
158 Nova Lite 1.0Amazon 1241 4,869±8.6 Not benchmarked $0.24
159 Gemma 2 27BGoogle 1228 19,950±5.4 Not benchmarked $0.65
160 Phi 4Microsoft 1228 5,580±8.1 Not benchmarked $0.14
161 Claude 3 SonnetRetiredAnthropic 1221 31,448±6.1 Not benchmarked $15.00
162 Nova Micro 1.0Amazon 1215 4,685±8.7 Not benchmarked $0.14
163 Command R (08-2024)Cohere 1197 2,714±11.0 Not benchmarked $0.60
164 Llama 3.1 8B InstructMeta Llama 1195 13,139±6.5 Not benchmarked $0.08
165 GPT-4OpenAI 1195 14,549±7.8 Not benchmarked $60.00
166 Claude 3 HaikuRetiredAnthropic 1194 34,258±5.9 Not benchmarked $1.25
167 Llama 3.2 3B InstructMeta Llama 1103 2,165±12.9 Not benchmarked $0.3325
168 Llama 3.2 1B InstructMeta Llama 1056 2,184±13.3 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 21, 2026, and rows that match no catalog model are left out. Every other column is a figure the board publishes for the same run.