Across 10 comparable benchmarks, Opus 4.5 has better reported results on 10 and worse on 0.
Moderate evidence10 of 10 shared results countedHow we compare
Price basis: Standard rates vs listed rates. The price section below shows the applicable periods.
| Fact | Opus 4.5 | Qwen3-30B-A3B-2507 |
|---|---|---|
| Context window | 200K tokens | 256K tokens |
| Input / 1M | $5.00 | — |
| Output / 1M | $25.00 | — |
| Blended (4:1) | $5.76 | — |
| Status | Available | Deprecated |
| Released | November 25, 2025 | July 29, 2025 |
Blended is 4:1 input to output with 90% cache hits at listed rates — set your own mix.
Mean of 5 shared benchmarks grouped by capability on a 0–100 scale. How averages are built
Opus 4.5 ahead on 3 of 3 counted
Opus 4.5 ahead on 1 of 1 counted
Opus 4.5 ahead on 2 of 2 counted
Opus 4.5 ahead on 2 of 2 counted
No shared comparable results for Abstract reasoning, Computer & tool use, Research & search, Long context, Multimodal, Cybersecurity.
Published scores, with matching modes where available. Gaps show Opus 4.5 relative to Qwen3-30B-A3B-2507. Reading the results
| Benchmark | Opus 4.5 | Qwen3-30B-A3B-2507 | Gap |
|---|---|---|---|
| LiveCodeBenchAlgorithmic Coding · Pass @K | 87.1Thinking · no tools | 43.2≠Normal · no tools | 2.02×#17 vs #92 of 113 |
| SWE-bench VerifiedRepository Engineering · Accuracy | 80.9Extended · tools | 22.0≠Thinking · no tools | +58.9 pts#9 vs #107 of 108 |
| Terminal Bench HardAgentic Development · Accuracy | 47.0Thinking · tools | 5.3Thinking · tools | +41.7 pts#15 vs #135 of 157 |
| AIME2025Mathematics · Accuracy | 91.3Thinking · no tools | 61.3≠Normal · no tools | +30.0 pts#34 vs #75 of 86 |
| CritPtScientific Reasoning · Score | 4.6Thinking · no tools | 0.3Thinking · no tools | 15.3×#73 vs #124 of 134 |
| GPQA DiamondScientific Reasoning · Accuracy | 87.0Extended · no tools | 70.4≠Normal · no tools | +16.6 pts#70 vs #138 of 200 |
| τ²-BenchService Workflows · Accuracy | 82.0Extended · tools | 49.0≠Thinking · tools | +33.0 pts#13 vs #33 of 40 |
| τ³-BankingService Workflows · Score | 24.7Thinking High · tools | 5.4≠Thinking · tools | 4.58×#48 vs #107 of 120 |
| HLEKnowledge Exams · Accuracy | 43.2Extended · tools | 9.8≠Thinking · no tools | +33.4 pts#72 vs #128 of 151 |
| MMLU-ProKnowledge Exams · Accuracy | 90.0Extended · no tools | 78.4≠Normal · no tools | +11.6 pts#1 vs #69 of 153 |
Algorithmic Coding · Pass @K
Repository Engineering · Accuracy
Agentic Development · Accuracy
Mathematics · Accuracy
Scientific Reasoning · Score
Scientific Reasoning · Accuracy
Service Workflows · Accuracy
Service Workflows · Score
A dash means no result is available.
| Benchmark | Opus 4.5 | Qwen3-30B-A3B-2507 |
|---|---|---|
| AIME 2026 | 93.3 | — |
| FrontierMath | 20.7 | — |
| FrontierMath - Tier 4 | 4.2 | — |
| FrontierMath Tier 4 v2 | 4.9 | — |
| FrontierMath v2 | 34.4 | — |
| HLE-Verified | 38.8 | — |
| IMO-ProofBench Advanced | 23.8 | — |
| Riemann-bench | 11.2 | — |
| SciCode | — | 33.0 |
| APEX-SWE | 38.7 | — |
| GSO | 26.5 | — |
| SWE-bench | 52.6 | — |
| SWE-bench Multilingual | 70.7 | — |
| SWE-Bench Pro - Commercial | 23.4 | — |
| SWE-Bench Pro - Public | 45.9 | — |
| Terminal Bench 2.0 | 59.3 | — |
| Vibe Code Bench v1.1 | 20.6 | — |
| WeirdML v2 | 63.7 | — |
| WeirdML v3 | 0.065 | — |
| Claw Bench | 91.5 | — |
| MCP-Atlas | 69.8 | — |
| Pinch Bench | 87.2 | — |
| ECI | 150 | — |
| LiveBench | 72.6 | — |
| METR Time Horizons v1.1 | 293 | — |
| Text Arena (Coding) | 1512 | — |
| Creative Writing | 1686 | — |
| IF Bench | 58.0 | — |
| EBR-bench | 14.3 | — |
| LongBench v2 | 64.4 | — |
| GDP.pdf | — | 0.4 |
| GeoBench ACW | 75.0 | — |
| MMMU | 80.7 | — |
| MMMU-Pro | 74.0 | — |
| VPCT | 40.0 | — |
| SAGE | 52.1 | — |
| τ²-Bench - Telecom | 92.3 | — |
| ARC-AGI-1 | 80.0 | — |
| ARC-AGI-2 | 37.6 | — |
| BALROG | 43.5 | — |
| SimpleBench | 62.0 | — |
| Vending-Bench 2 | 4967 | — |
| BrowseComp | — | 2.3 |
| MedCode | 49.2 | — |
| MedScribe | 85.3 | — |
Time-of-day providers use peak-hour rates; fixed-price providers use standard rates. Off-peak discounts remain in the published details.
Drag the handle above the bar for cache hits, the one below it for the input : output mix · 5% steps
Blended price = effective input rate at 90% cache hits × 80% + output rate × 20%
A blended cost needs a published input and output price on both sides, and one of these two does not have them yet.
Opus 4.5: Standard pricing. Anthropic official pricing (platform.claude.com/docs/en/about-claude/pricing) verified 2026-11-13
Qwen3-30B-A3B-2507: Listed text rates; pricing tier not confirmed.
| Price / 1M tokens | Opus 4.5 | Qwen3-30B-A3B-2507 | Ratio |
|---|---|---|---|
| Input | $5.00 | — | — |
| Output | $25.00 | — | — |
| Cached input | $0.50 | — | — |
| Cache write | — | — | — |
| Blended | $5.76 | — | — |
Estimates use the selected token mix. Cache writes, tool fees and long-context surcharges are excluded.
Reported cost per task, paired with the score from the same run. Settings and sources may differ; costs do not affect the verdict.
| Benchmark | Opus 4.5 | Qwen3-30B-A3B-2507 |
|---|---|---|
| ARC-AGI-1 | Not reported | |
| ARC-AGI-2 | Not reported | |
| WeirdML v3 | $8.7034 / task Average · Official score (0-1; higher is better): 0.065 Thinking High (With Tools) | Not reported |
| Attribute | Opus 4.5 | Qwen3-30B-A3B-2507 |
|---|---|---|
| Availability | Available | Deprecated |
| Provider | Anthropic | Alibaba |
| Model type | Reasoning model | Chat model |
| First release | November 25, 2025 | July 29, 2025 |
| Context window | 200K tokens | 256K tokens |
| Max output | 64K tokens | 16K tokens |
| Total parameters | — | 30.5B |
| Active parameters | — | 3.3B |
| Architecture | Undisclosed | Mixture of Experts (MoE) |
| Documented capabilities | Reasoning, Multilingual | Multilingual |
| Knowledge cutoff | 2025-03 | — |
| Input modalities | Text, Image | Text |
| Output modalities | Text | Text |
| Weights | Closed / API only | Open weights |
| Licence | — | Apache 2.0 |
| Commercial use | Proprietary | Commercial use allowed |
These are reported-score comparisons, not controlled head-to-head tests.
What people found comparing these models, or using either one. Comments also appear on the models' own pages.
Used Opus 4.5 or Qwen3-30B-A3B-2507? Sign in with Google to share what worked, what did not, and which API or setup you tested.
No community comments on either model yet.
Alternatives with the most benchmark overlap for this matchup.