Across 8 comparable benchmarks, Qwen3.7-Plus has better reported results on 6 and worse on 2.
Moderate evidence8 of 8 shared results countedHow we compare
Price basis: Listed rates vs standard rates. The price section below shows the applicable periods.
| Fact | Qwen3.7-Plus | OpenAI o3 |
|---|---|---|
| Context window | 1M tokens | 200K tokens |
| Input / 1M | $0.400 | $2.00 |
| Output / 1M | $1.60 | $8.00 |
| Blended (4:1) | $0.410 | $2.12 |
| Status | Available | Deprecated |
| Released | May 31, 2026 | April 16, 2025 |
Blended is 4:1 input to output with 90% cache hits at listed rates — set your own mix.
Mean of 6 shared benchmarks grouped by capability on a 0–100 scale. How averages are built
Qwen3.7-Plus ahead on 1 of 1 counted
Qwen3.7-Plus ahead on 1 of 1 counted
Split 1–1 of 2 counted
Qwen3.7-Plus ahead on 1 of 1 counted
Qwen3.7-Plus ahead on 1 of 1 counted
OpenAI o3 ahead on 1 of 1 counted
No shared comparable results for Abstract reasoning, Research & search, Long context, Cybersecurity.
Published scores, with matching modes where available. Gaps show Qwen3.7-Plus relative to OpenAI o3. Reading the results
| Benchmark | Qwen3.7-Plus | OpenAI o3 | Gap |
|---|---|---|---|
| Terminal Bench HardAgentic Development · Accuracy | 47.0Thinking · tools | 37.1Thinking · tools | +9.9 pts#15 vs #43 of 157 |
| FrontierMath v2Mathematics · Accuracy (verification_code) | 34.4Normal · tools | 33.3≠Thinking High · no tools | +1.1 pts#67 vs #69 of 85 |
| CritPtScientific Reasoning · Score | 9.1Thinking · no tools | 1.1Thinking · no tools | 8.27×#58 vs #103 of 134 |
| GPQA DiamondScientific Reasoning · Accuracy | 81.8Normal · no tools | 83.3≠Thinking · no tools | −1.5 pts#100 vs #94 of 200 |
| OSWorld-VerifiedDesktop Workflows · Accuracy | 73.3Unspecified Reasoning · tools | 23.0Unspecified Reasoning · tools | +50.3 pts#20 vs #34 of 36 |
| MMMU-ProVisual Understanding · Accuracy | 80.5Thinking · no tools | 76.4≠Reported best | +4.1 pts#28 vs #56 of 136 |
| SAGEService Workflows · Accuracy (%) | 39.3Unspecified Reasoning · tools | 41.8≠Thinking High · tools | −2.5 pts#59 vs #56 of 82 |
| ECICapability Indices · ECI score (capability index, higher is better) | 147Reported best | 147Reported best | 1.00×#60 vs #62 of 168 |
Agentic Development · Accuracy
Mathematics · Accuracy (verification_code)
Scientific Reasoning · Score
Scientific Reasoning · Accuracy
Desktop Workflows · Accuracy
Visual Understanding · Accuracy
Service Workflows · Accuracy (%)
Capability Indices · ECI score (capability index, higher is better)
A dash means no result is available.
| Benchmark | Qwen3.7-Plus | OpenAI o3 |
|---|---|---|
| AIME 2024 | — | 91.6 |
| AIME2025 | — | 88.9 |
| FrontierMath | — | 10.3 |
| FrontierMath - Tier 4 | — | 2.1 |
| HLE | — | 20.3 |
| IMO-ProofBench | — | 20.5 |
| IMO-ProofBench Advanced | — | 20.5 |
| MATH-500 | — | 99.2 |
| MMLU-Pro | — | 85.6 |
| SciCode | 46.1 | — |
| Aider-Polyglot | — | 81.3 |
| Code Migration | 12.9 | — |
| CodeClash | — | 1343 |
| FrontierCode 1.1 | 10.2 | — |
| GSO | — | 8.8 |
| LiveCodeBench | — | 75.8 |
| SWE-bench Verified | — | 69.1 |
| Terminal-Bench 1.0 | — | 30.2 |
| Terminal-Bench 4.0 | 1.0 | — |
| Vibe Code Bench v1.1 | 46.4 | — |
| WeirdML v2 | — | 52.4 |
| OSWorld 2.0 | 21.5 | — |
| METR Time Horizons v1.1 | — | 91.3 |
| Creative Writing | — | 1675 |
| IF Bench | 78.0 | — |
| Fiction.liveBench | — | 88.9 |
| GDP.pdf | 12.2 | — |
| GeoBench ACW | — | 74.0 |
| MMMU | — | 82.9 |
| VPCT | — | 52.0 |
| AutomationBench | 3.7 | — |
| EMB (Excel Modeling) | 49.3 | — |
| Finance Agent v2 | 38.2 | — |
| Harvey Lab-AA | 81.8 | — |
| Legal Research Bench | 16.4 | — |
| Tax Agent Bench | 10.5 | — |
| τ³-Banking | 17.5 | — |
| ARC-AGI-1 | — | 60.8 |
| ARC-AGI-2 | — | 6.5 |
| SimpleBench | — | 53.1 |
| GAIA | — | 28.5 |
| SimpleQA | — | 49.4 |
| MedCode | — | 47.3 |
| MedScribe | — | 76.7 |
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%
Qwen3.7-Plus costs81%lessthan OpenAI o3 per million tokens — 5.2× cheaper.Using listed rates vs standard rates at this token mix.
Qwen3.7-Plus: International pricing. context_length <= 256000 Alibaba Model Studio International (Singapore) context_length > 256000; context_length <= 1000000
OpenAI o3: Standard pricing. OpenAI official pricing (developers.openai.com/api/docs/pricing) verified 2026-11-13; standard tier; Deprecated; shutdown 2026-12-11 (replacement: gpt-6.1-sol)
| Price / 1M tokens | Qwen3.7-Plus | OpenAI o3 | Ratio |
|---|---|---|---|
| Input | $0.40 | $2.00 | 0.20× |
| Output | $1.60 | $8.00 | 0.20× |
| Cached input | $0.08 | $0.50 | 0.16× |
| Cache write | — | — | — |
| Blended | $0.41 | $2.12 | 0.19× |
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 | Qwen3.7-Plus | OpenAI o3 |
|---|---|---|
| ARC-AGI-1 | Not reported | |
| ARC-AGI-2 | Not reported | $0.4787 / task Average · ARC-AGI-2 Score: 3.0 Thinking Medium (No Tools) |
| AutomationBench | $0.05 / task Average · Pass Rate: 3.7 Reported best (effort unspecified) · zapier-private-heldout | Not reported |
| Code Migration | $0.4192 / task Average · Hidden-test pass rate (%): 12.9 Unspecified Reasoning (With Tools) | Not reported |
| EMB (Excel Modeling) | Not reported | |
| Finance Agent v2 | Not reported | |
| Legal Research Bench | Not reported | |
| SAGE | Not reported | |
| Tax Agent Bench | $0.0939 / task Average · Accuracy (%, rubric × citation quality): 10.5 Unspecified Reasoning (With Tools) | Not reported |
| Vibe Code Bench v1.1 | Not reported |
| Attribute | Qwen3.7-Plus | OpenAI o3 |
|---|---|---|
| Availability | Available | Deprecated |
| Provider | Alibaba | OpenAI |
| Model type | Reasoning model | Reasoning model |
| First release | May 31, 2026 | April 16, 2025 |
| Context window | 1M tokens | 200K tokens |
| Max output | 64K tokens | 100K tokens |
| Architecture | Undisclosed | Undisclosed |
| Documented capabilities | Reasoning, Multilingual, Coding, Function calling, Tool use, Long context | Reasoning, Multilingual |
| Input modalities | Text, Image, Video | Text, Image |
| Output modalities | Text | Text |
| Weights | Closed / API only | Closed / API only |
| Commercial use | Commercial use allowed | Proprietary |
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 Qwen3.7-Plus or OpenAI o3? 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.