Qwen2.5 72B Instruct
Qwen2.5 72B is the latest series of Qwen large language models. Qwen2.5 brings the following improvements upon Qwen2: - Significantly more knowledge and has greatly improved capabilities in coding an…
qwen/qwen-2.5-72b-instruct
Qwen2.5 72B is the latest series of Qwen large language models. Qwen2.5 brings the following improvements upon Qwen2: - Significantly more knowledge and has greatly improved capabilities in coding and...
Specifications & capabilities
- Input
- text
- Output
- text
- Context window · tokens
- 32768
- Knowledge cutoff
- 2024-06-30
- Published model ID
- Qwen2.5-72B-Instruct
- Capabilities
- structuredOutputs, toolCalling
Evaluations
21–40 / 76
1,320.492
- source id
- lmarena
- leaderboard name
- LMArena Text Style Control French
- dimension
- style
- metric
- Arena rating
- rank
- 237
- sample size
- 340
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Qwen2.5-72B-Instruct
- confidence lower
- 1287.3556605488727
- confidence upper
- 1353.6292032217677
Original result ↗1,255.276
- source id
- lmarena
- leaderboard name
- LMArena Text Spanish
- dimension
- general
- metric
- Arena rating
- rank
- 243
- sample size
- 347
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Qwen2.5-72B-Instruct
- confidence lower
- 1224.3369456436349
- confidence upper
- 1286.2156480012231
Original result ↗1,293.017
- source id
- lmarena
- leaderboard name
- LMArena Text Style Control Spanish
- dimension
- style
- metric
- Arena rating
- rank
- 247
- sample size
- 347
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Qwen2.5-72B-Instruct
- confidence lower
- 1261.7913927124227
- confidence upper
- 1324.2418578289069
Original result ↗1,233.361
- source id
- lmarena
- leaderboard name
- LMArena Text German
- dimension
- general
- metric
- Arena rating
- rank
- 247
- sample size
- 926
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Qwen2.5-72B-Instruct
- confidence lower
- 1214.072887591549
- confidence upper
- 1252.6484637715453
Original result ↗1,290.555
- source id
- lmarena
- leaderboard name
- LMArena Text Industry Mathematical
- dimension
- general
- metric
- Arena rating
- rank
- 249
- sample size
- 4565
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Qwen2.5-72B-Instruct
- confidence lower
- 1281.7392748514412
- confidence upper
- 1299.3698249340546
Original result ↗1,265.872
- source id
- lmarena
- leaderboard name
- LMArena Text Style Control German
- dimension
- style
- metric
- Arena rating
- rank
- 252
- sample size
- 926
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Qwen2.5-72B-Instruct
- confidence lower
- 1246.44906376522
- confidence upper
- 1285.2944525986436
Original result ↗1,282.563
- source id
- lmarena
- leaderboard name
- LMArena Text Math
- dimension
- general
- metric
- Arena rating
- rank
- 253
- sample size
- 5415
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Qwen2.5-72B-Instruct
- confidence lower
- 1274.3075899950577
- confidence upper
- 1290.818158971014
Original result ↗1,309.177
- source id
- lmarena
- leaderboard name
- LMArena Text Style Control Industry Mathematical
- dimension
- style
- metric
- Arena rating
- rank
- 257
- sample size
- 4565
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Qwen2.5-72B-Instruct
- confidence lower
- 1300.2950660441709
- confidence upper
- 1318.0581112059463
Original result ↗1,295.767
- source id
- lmarena
- leaderboard name
- LMArena Text Style Control Math
- dimension
- style
- metric
- Arena rating
- rank
- 258
- sample size
- 5415
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Qwen2.5-72B-Instruct
- confidence lower
- 1287.4680814251074
- confidence upper
- 1304.0658291215964
Original result ↗1,330.565
- source id
- lmarena
- leaderboard name
- LMArena Text Style Control Industry Legal And Government
- dimension
- style
- metric
- Arena rating
- rank
- 260
- sample size
- 2386
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Qwen2.5-72B-Instruct
- confidence lower
- 1317.7118215891987
- confidence upper
- 1343.418043644272
Original result ↗1,322.674
- source id
- lmarena
- leaderboard name
- LMArena Text Style Control Chinese
- dimension
- style
- metric
- Arena rating
- rank
- 262
- sample size
- 3329
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Qwen2.5-72B-Instruct
- confidence lower
- 1311.5476480913449
- confidence upper
- 1333.800835156678
Original result ↗1,272.559
- source id
- lmarena
- leaderboard name
- LMArena Text Chinese
- dimension
- general
- metric
- Arena rating
- rank
- 262
- sample size
- 3329
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Qwen2.5-72B-Instruct
- confidence lower
- 1261.5413356649033
- confidence upper
- 1283.5769897546988
Original result ↗1,287.961
- source id
- lmarena
- leaderboard name
- LMArena Text Industry Legal And Government
- dimension
- general
- metric
- Arena rating
- rank
- 263
- sample size
- 2386
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Qwen2.5-72B-Instruct
- confidence lower
- 1275.151000799584
- confidence upper
- 1300.770089160783
Original result ↗1,244.783
- source id
- lmarena
- leaderboard name
- LMArena Text Expert
- dimension
- general
- metric
- Arena rating
- rank
- 265
- sample size
- 2397
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Qwen2.5-72B-Instruct
- confidence lower
- 1232.6433046580028
- confidence upper
- 1256.9232896692365
Original result ↗1,292.294
- source id
- lmarena
- leaderboard name
- LMArena Text Coding
- dimension
- general
- metric
- Arena rating
- rank
- 267
- sample size
- 6688
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Qwen2.5-72B-Instruct
- confidence lower
- 1284.690679466615
- confidence upper
- 1299.8971135091983
Original result ↗1,263.747
- source id
- lmarena
- leaderboard name
- LMArena Text Russian
- dimension
- general
- metric
- Arena rating
- rank
- 267
- sample size
- 5776
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Qwen2.5-72B-Instruct
- confidence lower
- 1255.2761518350896
- confidence upper
- 1272.218779607918
Original result ↗1,281.424
- source id
- lmarena
- leaderboard name
- LMArena Text Longer Query
- dimension
- general
- metric
- Arena rating
- rank
- 269
- sample size
- 6008
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Qwen2.5-72B-Instruct
- confidence lower
- 1273.3630265802299
- confidence upper
- 1289.4845811327898
Original result ↗1,297.203
- source id
- lmarena
- leaderboard name
- LMArena Text Style Control Russian
- dimension
- style
- metric
- Arena rating
- rank
- 270
- sample size
- 5776
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Qwen2.5-72B-Instruct
- confidence lower
- 1288.699257513903
- confidence upper
- 1305.7060024693267
Original result ↗1,292.11
- source id
- lmarena
- leaderboard name
- LMArena Text Industry Software And It Services
- dimension
- general
- metric
- Arena rating
- rank
- 270
- sample size
- 10448
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Qwen2.5-72B-Instruct
- confidence lower
- 1285.5327214625363
- confidence upper
- 1298.6867646251994
Original result ↗1,354.748
- source id
- lmarena
- leaderboard name
- LMArena Text Style Control Coding
- dimension
- style
- metric
- Arena rating
- rank
- 271
- sample size
- 6688
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Qwen2.5-72B-Instruct
- confidence lower
- 1347.093265426065
- confidence upper
- 1362.4031261976147
Original result ↗Published prices
1–6 / 6
$0.36
- Inference provider
- deepInfra
- Platform
- DeepInfra
- Unit
- input_tokens_per_million
- Currency
- USD
$0.40
- Inference provider
- deepInfra
- Platform
- DeepInfra
- Unit
- output_tokens_per_million
- Currency
- USD
$0.36
- Inference provider
- openRouter
- Platform
- OpenRouter
- Unit
- input_tokens_per_million
- Currency
- USD
$0.40
- Inference provider
- openRouter
- Platform
- OpenRouter
- Unit
- output_tokens_per_million
- Currency
- USD
$0.59
- Inference provider
- siliconFlow
- Platform
- SiliconFlow
- Unit
- input_tokens_per_million
- Currency
- USD
- Billing label
- Input tokens (per 1M)
$0.59
- Inference provider
- siliconFlow
- Platform
- SiliconFlow
- Unit
- output_tokens_per_million
- Currency
- USD
- Billing label
- Output tokens (per 1M)
Provider specifications & access
1–2 / 2
- source model id
- HuggingFace/qwen-qwen2.5-72b-instruct@1
- hosting
- foundry-managed-compute
- license
- other
- source model id
- Qwen/Qwen2.5-72B-Instruct
- hosting
- siliconflow-hosted
- max output tokens
- 4096
- capabilities
- structuredOutputs
- toolCalling
Safety assessments
1–1 / 1
26 / 100
- source id
- stanfordFMTI
- canonical model id
- qwen/qwen-2.5-72b-instruct
- taxonomy
- transparency
- hazard category
- transparency
- hazard name
- Organization transparency
- policy area
- Alibaba
- assessment type
- organization-level disclosure
- metric
- disclosure_score
- result label
- 26 / 100
- sample size
- 100
- updated at
- 2026-11-09T18:08:05.227Z
Source specification observations
1–5 / 5
- field
- context_length
- value
- 32768
- normalized value
- 32768
- scope
- source-model
- source id
- openRouter
- confidence
- 1
- field
- context_length
- value
- 33K
- scope
- source-model
- source id
- siliconFlow
- confidence
- 1
- field
- knowledge_cutoff
- reported field
- knowledge_cutoff
- value
- 2024-06-30
- normalized value
- 2024-06-30
- precision
- day
- scope
- source-model
- source id
- openRouter
- confidence
- 1
- field
- max_output_tokens
- value
- 16384
- normalized value
- 16384
- scope
- source-model
- source id
- openRouter
- confidence
- 1
- field
- max_output_tokens
- value
- 4K
- scope
- source-model
- source id
- siliconFlow
- confidence
- 1
Explore more models