Qwen: Qwen3 30B A3B Instruct 2507
Released Jul 29, 2025Ranked in:Text
Try it on:
Qwen3-30B-A3B-Instruct-2507 is a 30.5B-parameter mixture-of-experts language model from Qwen, with 3.3B active parameters per inference. It operates in non-thinking mode and is designed for high-quality instruction following, multilingual understanding, and...
Best overall rank
#143
▼ 1 vs 7d ago
Total arena votes
141,989
Across 29 (subset, category) entries
Providers on OR
6
Alibaba + others
First seen
2026-05-08
61 days tracked
Trend
Pricing
Per token
- Input (per 1M)
- $0.048
- Output (per 1M)
- $0.193
Capabilities
Modality
text->textContext
131K tokens
Tokenizer
Qwen3
Knowledge cutoff
2025-06-30
Max output
32K tokens
Moderation
Unmoderated
Hugging Face
Supported parameters
frequency_penalty
logit_bias
logprobs
max_tokens
min_p
presence_penalty
repetition_penalty
response_format
seed
stop
structured_outputs
temperature
tool_choice
tools
top_k
top_logprobs
top_p
Providers
| Provider | Region / Tag | Context | Input/M | Output/M | Uptime 1d | Latency | Quant | Cache |
|---|---|---|---|---|---|---|---|---|
| Alibaba | alibaba | 131K | $0.130 | $0.520 | 99.94% | - | - | - |
| StreamLake | streamlake | 128K | $0.048 | $0.193 | 99.84% | - | - | - |
| WandB | wandb/bf16 | 262K | $0.100 | $0.300 | 98.62% | - | bf16 | - |
| Nebius | nebius/fp8 | 262K | $0.100 | $0.300 | 95.37% | - | fp8 | - |
| SiliconFlow | siliconflow/fp8 | 262K | $0.090 | $0.300 | 85.19% | - | fp8 | - |
| Phala | phala | 262K | $0.150 | $0.550 | 42.44% | - | - | - |
Per-category ranks
Text
| Rank | Category | Variant | Trend | Elo | Votes |
|---|---|---|---|---|---|
| #111 | French | - | 1420 | 306 | |
| #114 | Chinese | - | 1436 | 1,321 | |
| #115 | Japanese | - | 1325 | 704 | |
| #116 | Spanish | - | 1387 | 633 | |
| #125 | Coding | - | 1440 | 4,657 | |
| #125 | Industry Business And Management And Financial Operations | - | 1396 | 4,170 | |
| #126 | Industry Software And It Services | - | 1429 | 8,195 | |
| #128 | Industry Mathematical | - | 1400 | 1,206 | |
| #134 | German | - | 1359 | 486 | |
| #134 | Non English | - | 1370 | 12,664 | |
| #138 | Hard Prompts | - | 1407 | 11,066 | |
| #138 | Korean | - | 1314 | 567 | |
| #140 | Hard Prompts English | - | 1416 | 5,624 | |
| #142 | Exclude Ties | - | 1359 | 16,678 | |
| #143 | Industry Medicine And Healthcare | - | 1399 | 1,347 | |
| #143 | Overall | - | 1383 | 23,720 | |
| #144 | Multi Turn | - | 1383 | 4,070 | |
| #145 | Expert | - | 1392 | 1,147 | |
| #146 | English | - | 1393 | 11,048 | |
| #147 | Longer Query | - | 1381 | 4,878 | |
| #147 | Polish | - | 1345 | 1,494 | |
| #148 | Industry Life And Physical And Social Science | - | 1394 | 3,682 | |
| #148 | Math | - | 1381 | 1,427 | |
| #148 | Russian | - | 1366 | 1,227 | |
| #149 | Industry Legal And Government | - | 1383 | 1,491 | |
| #149 | Instruction Following | - | 1366 | 5,961 | |
| #155 | Industry Entertainment And Sports And Media | - | 1333 | 4,143 | |
| #162 | Industry Writing And Literature And Language | - | 1343 | 5,095 | |
| #172 | Creative Writing | - | 1321 | 2,982 |