BlogLLM Benchmark Scores as Published, Side by Side
Qwen3-30B-A3B-Thinking-2507: Benchmark Scores as Published
Every result the catalog holds for Qwen3-30B-A3B-Thinking-2507: 26 tests in 9 areas, from 1 page. Each was printed by the company named beside it. Each number is as printed; nothing is ranked or rescored.
Developer AlibabaReleased 2025-07-30Context window 262KInput TextOutput TextWeights Open (Apache 2.0)Data version 2026103001, as of 2026-10-30
Agentic Coding
| Test | Value | Printed by | Setup as printed |
|---|---|---|---|
| Terminal-Bench Hard | 5% | NVIDIA, NVIDIA Nemotron 3 Nano 30B-A3B model cardchecked 2026-10-15 | Effort: thinking |
| SWE-bench (split not stated) | 22% | NVIDIA, NVIDIA Nemotron 3 Nano 30B-A3B model cardchecked 2026-10-15 | Effort: thinking; Harness: OpenHands |
Science and Math
| Test | Value | Printed by | Setup as printed |
|---|---|---|---|
| AIME 2025 | 85% | NVIDIA, NVIDIA Nemotron 3 Nano 30B-A3B model cardchecked 2026-10-15 | Effort: thinking; Tools: none |
| SciCode | 33% | NVIDIA, NVIDIA Nemotron 3 Nano 30B-A3B model cardchecked 2026-10-15 | Effort: thinking |
| GPQA | 73.4% | NVIDIA, NVIDIA Nemotron 3 Nano 30B-A3B model cardchecked 2026-10-15 | Effort: thinking; Tools: none |
| MiniF2F (pass@1) | 5.7% | NVIDIA, NVIDIA Nemotron 3 Nano 30B-A3B model cardchecked 2026-10-15 | Effort: thinking |
| MiniF2F (pass@32) | 16.8% | NVIDIA, NVIDIA Nemotron 3 Nano 30B-A3B model cardchecked 2026-10-15 | Effort: thinking |
Long Context
| Test | Value | Printed by | Setup as printed |
|---|---|---|---|
| AA-LCR | 59% | NVIDIA, NVIDIA Nemotron 3 Nano 30B-A3B model cardchecked 2026-10-15 | Effort: thinking |
| RULER-100 at 1M | 77.5% | NVIDIA, NVIDIA Nemotron 3 Nano 30B-A3B model cardchecked 2026-10-15 | Effort: thinking; Context: 1048576 |
| RULER-100 at 256K | 89.4% | NVIDIA, NVIDIA Nemotron 3 Nano 30B-A3B model cardchecked 2026-10-15 | Effort: thinking; Context: 262144 |
| RULER-100 at 512K | 84% | NVIDIA, NVIDIA Nemotron 3 Nano 30B-A3B model cardchecked 2026-10-15 | Effort: thinking; Context: 524288 |
General Knowledge and Reasoning
| Test | Value | Printed by | Setup as printed |
|---|---|---|---|
| Humanity's Last Exam (no tools) | 9.8% | NVIDIA, NVIDIA Nemotron 3 Nano 30B-A3B model cardchecked 2026-10-15 | Effort: thinking; Tools: none |
| MMLU-Pro | 80.9% | NVIDIA, NVIDIA Nemotron 3 Nano 30B-A3B model cardchecked 2026-10-15 | Effort: thinking |
Code Generation
| Test | Value | Printed by | Setup as printed |
|---|---|---|---|
| LiveCodeBench v6 | 66% | NVIDIA, NVIDIA Nemotron 3 Nano 30B-A3B model cardchecked 2026-10-15 | Effort: thinking |
Tool Use and Workflows
| Test | Value | Printed by | Setup as printed |
|---|---|---|---|
| τ²-bench Telecom | 26.3% | NVIDIA, NVIDIA Nemotron 3 Nano 30B-A3B model cardchecked 2026-10-15 | Effort: thinking |
| τ²-bench Retail | 58.8% | NVIDIA, NVIDIA Nemotron 3 Nano 30B-A3B model cardchecked 2026-10-15 | Effort: thinking |
| τ²-bench Airline | 58% | NVIDIA, NVIDIA Nemotron 3 Nano 30B-A3B model cardchecked 2026-10-15 | Effort: thinking |
| BFCL v4 | 46.4% | NVIDIA, NVIDIA Nemotron 3 Nano 30B-A3B model cardchecked 2026-10-15 | Effort: thinking |
| τ²-bench (average of 3 domains) | 47.7% | NVIDIA, NVIDIA Nemotron 3 Nano 30B-A3B model cardchecked 2026-10-15 | Effort: thinking |
Instruction Following
| Test | Value | Printed by | Setup as printed |
|---|---|---|---|
| IFBench | 51 | NVIDIA, NVIDIA Nemotron 3 Nano 30B-A3B model cardchecked 2026-10-15 | Effort: thinking |
| MultiChallenge | 44.8% | NVIDIA, NVIDIA Nemotron 3 Nano 30B-A3B model cardchecked 2026-10-15 | Effort: thinking |
Multilingual
| Test | Value | Printed by | Setup as printed |
|---|---|---|---|
| MMLU-ProX | 77.6% | NVIDIA, NVIDIA Nemotron 3 Nano 30B-A3B model cardchecked 2026-10-15 | Effort: thinking |
| WMT24++ (XCOMET-XXL) | 85.6 | NVIDIA, NVIDIA Nemotron 3 Nano 30B-A3B model cardchecked 2026-10-15 | Effort: thinking |
Preference and Composite Rankings
| Test | Value | Printed by | Setup as printed |
|---|---|---|---|
| Arena-Hard v2 (average) | 57.8% | NVIDIA, NVIDIA Nemotron 3 Nano 30B-A3B model cardchecked 2026-10-15 | Effort: thinking |
| Arena-Hard v2 (creative writing) | 66% | NVIDIA, NVIDIA Nemotron 3 Nano 30B-A3B model cardchecked 2026-10-15 | Effort: thinking |
| Arena-Hard v2 (hard prompt) | 49.6% | NVIDIA, NVIDIA Nemotron 3 Nano 30B-A3B model cardchecked 2026-10-15 | Effort: thinking |
More from Alibaba
- Qwen3.8-Max
- Qwen3.7-Plus
- Qwen3.6-27B
- Qwen3.6-35B-A3B
- Qwen3.6-Plus
- Qwen3.5-122B-A10B
- Qwen3.5-27B
- Qwen3.5-35B-A3B
- Qwen3.5-397B-A17B
- Qwen3-VL-32B-Instruct
- Qwen3-VL-32B-Thinking
- Qwen3-VL-8B-Instruct
- Qwen3-VL-8B-Thinking
- Qwen3-VL-235B-A22B
- Qwen3-VL-235B-A22B-Thinking
- Qwen3-Next-80B-A3B
- Qwen3-30B-A3B-Instruct-2507
- Qwen3-Coder-Plus
- Qwen3-235B-A22B
- Qwen3-32B
- Qwen3-8B
- QwQ-32B-Preview
- Qwen-Max
- Qwen3-Max-Thinking
- Qwen3.7-Max
- Qwen3.8-2.4T-A95B
- Qwen3.8-27B
- Qwen3.8-Flash-Next
Every number here is read from the same catalog file as the benchmark table, data version 2026103001. Where one page printed the model under several setups, each value is listed. The catalog is public in armanobosyan/sugra-llm-benchmarks; a wrong number can be reported from the table, with Report an error under the value, or as an issue in that repository.