BenchLeader
Menu
Best LLMsChoose a modelCoding plansLeaderboardsModelsBenchmarksProvidersReleases9

o3 vs Qwen3.7

Full profiles: o3 (OpenAI) and Qwen3.7 (Alibaba): every benchmark, price and rank.

Updated · Data from 17 sources

As of 29 Oct 2026, o3 and Qwen3.7 are neck and neck on quality (61.0 vs 60.3 on the BenchLeader Index, inside the ±5.3 margin), and they cost about the same at $3.50 vs $3.75 per 1M tokens blended. Choose o3 for agents & tools (70 vs 49), maths (71 vs 58), and human preference (61 vs 56) and fast first answers (5.6 s vs 14.1 s); choose Qwen3.7 for instruction following (78 vs 65), reasoning (66 vs 61), and knowledge (61 vs 56), where it also streams faster.

Key facts (as of 29 Oct 2026)

  • o3 scores 61.0 on the BenchLeader Index and Qwen3.7 scores 60.3 (BenchLeader, 29 Oct 2026).
  • o3 costs $3.50 per 1M tokens blended (list price, 29 Oct 2026).
  • Qwen3.7 costs $3.75 per 1M tokens blended (list price, 29 Oct 2026).
  • Qwen3.7 streams faster than o3 (Artificial Analysis, 7-day median, 29 Oct 2026).
  • Of the 16 benchmarks both models have, Qwen3.7 leads 16 (BenchLeader, 29 Oct 2026).
o3 benchmarks OpenAI Qwen3.7 benchmarks max AlibabaOpen in the comparison tool

Which to pick for…

The pick's numbers come first. Category scores on the BenchLeader scale (50 is the average model, 15 points one standard deviation). High confidence means a lead of half a standard deviation or more; under one point is called either.

Use casePickWhyConfidence
Codingo362 vs 59 category score; Arena Coding 1460 vs 1523Medium
Agents & tool useo370 vs 49 category score; Terminal-Bench Hard 37.1% vs 50.8%High
Mathso371 vs 58 category score; Arena Maths 1448 vs 1482High
ReasoningQwen3.766 vs 61 category score; Arena Hard Prompts 1495 vs 1441Medium
KnowledgeQwen3.761 vs 56 category scoreMedium
Long documentsQwen3.764 vs 62 category score; AA-LCR v1.1 79.0% vs 74.7%Medium
Following instructionsQwen3.778 vs 65 category score; IFBench 80.5% vs 71.4%High
Chat quality (human preference)o361 vs 56 on Arena votesMedium
Lowest costEither$3.50 vs $3.75 per 1M blended; agentic coding session $0.152 vs $0.180–
Fastest first answero35.6 s (o3) vs 14.1 s (Qwen3.7 (max)) to the first answer token–
High volume on a budgetNeither flagshipA smaller model is usually the better fit: Cheapest good LLMs, Fastest LLMs–

Key differences

  • o3 and Qwen3.7 (max) are neck and neck on quality (61.0 vs 60.3, within the ±5.3 margin).
  • o3 is stronger in agents & tools, coding, human preference, maths, multimodal.
  • Qwen3.7 (max) is stronger in instruction following, knowledge, long context, reasoning.
  • They cost about the same ($3.50 per 1M blended).
  • Qwen3.7 (max) streams 1.3× faster (201 vs 151 tokens per second).

At a glance

Speco3Qwen3.7
DeveloperOpenAIAlibaba
Released16 Apr 202519 May 2026
Context window (tokens)200,0001,000,000
Compared ato3Qwen3.7 (max)
Open weightsNoNo
Price in / out / cached input per 1M$2.00 / $8.00 / $0.500$2.50 / $7.50 / $0.500

Category by category

Category scores on the BenchLeader scale: 50 is the average evaluated model, 15 points is one standard deviation. A gap under one point is called level.

Categoryo3Qwen3.7 (max)Leader
Reasoning60.966.3Qwen3.7
Coding61.859.1o3
Agents & tools70.349.3o3
Maths70.558.1o3
Knowledge56.161.2Qwen3.7
Instruction following65.178.0Qwen3.7
Human preference61.155.6o3
Multimodal56.7–not comparable
Long context62.164.3Qwen3.7

Where sources disagree

Across the 16 benchmarks both have, o3 leads 0, Qwen3.7 leads 16. Every overall index that rates both puts Qwen3.7 ahead.

Overall indexo3Qwen3.7 (max)Leader
BenchLeader Index61.060.3neck and neck
Arena Text14321474Qwen3.7

Each publisher runs its own tasks, harnesses and effort settings, so their overall verdicts can differ; BenchLeader reconciles them on one scale. † measured at another effort setting of the same model (the publisher did not test the one compared here).

Price, speed and latency

List prices blended at three input tokens per output token. Per-task prices use the token counts on the methodology page; suite cost is what Artificial Analysis paid to run its whole Intelligence Index.

Measureo3Qwen3.7 (max)
Blended price per 1M tokens$3.50$3.75
Input / output per 1M$2.00 / $8.00$2.50 / $7.50
Cached input per 1M$0.500$0.500
Price per task: chat reply$0.0032$0.0033
Price per task: summarize a 30-page report$0.029$0.035
Price per task: code edit$0.024$0.026
Price per task: agentic coding session$0.152$0.180
Price per task: structured extraction$0.0056$0.0065
Output speed151 tok/s201 tok/s
Time to first answer5.6 s14.1 s
Time to a complete answer8.9 s16.6 s

Each model is compared at its best-ranked reasoning-effort setting. o3 scores 61.0 and takes 6 s to its first answer token; o3 (high) scores 53.8 in 6 s, o3 (medium) scores 53.3 in 6 s. Qwen3.7 (max) scores 60.3 and takes 14 s to its first answer token. Higher effort means more thinking before the answer: better scores, longer waits and more tokens billed. How reasoning effort changes scores and cost.

Every benchmark

127 benchmarks, grouped by category; each name links to the board and its leaders. † measured at another effort setting of the same model, shown for reference and not counted as a win.

MetricPublishero3Qwen3.7 (max)
BenchLeader IndexBenchLeader61.060.3
Agents & tools scoreBenchLeader70.349.3
Coding scoreBenchLeader61.859.1
Human preference scoreBenchLeader61.155.6
Instruction following scoreBenchLeader65.178.0
Knowledge scoreBenchLeader56.161.2
Long context scoreBenchLeader62.164.3
Maths scoreBenchLeader70.558.1
Multimodal scoreBenchLeader56.7–
Reasoning scoreBenchLeader60.966.3
Blended price $/MBenchLeader$3.50$3.75
Output speedBenchLeader151 tok/s201 tok/s
Time to first answerBenchLeader5.6 s14.1 s
Context windowBenchLeader200,000 tokens1,000,000 tokens
Reasoning
GPQA DiamondEpoch AI Benchmarking Hub81.8%†90.9%
Humanity's Last ExamScale AI / CAIS20.3%†–
SimpleBenchSimpleBench53.1%†70.4%
Arena Hard PromptsArena (LMArena)14411495
LiveBench 1.0 ReasoningLiveBench–83.3%
GPQA Diamond (AA)Artificial Analysis82.7%92.3%
Humanity's Last Exam (AA)Artificial Analysis20.1%40.5%
GPQA Diamond (Vals)Vals AI84.1%†90.2%
Kagi LLM BenchmarkKagi LLM Benchmark67.6%–
GPQA Diamond (HELM)HELM Capabilities75.3%–
ARC-AGI-1ARC Prize60.8%†–
ARC-AGI-2ARC Prize6.5%†–
CritPtArtificial Analysis1.1%13.4%
SciPredictScale AI SEAL17.9%–
Chess PuzzlesEpoch AI Benchmarking Hub36.0%†26.0%
Mystery Game PuzzlesEpoch AI Benchmarking Hub29.0%†32.0%
CL-benchEpoch AI Benchmarking Hub17.8%†–
LMCAEpoch AI Benchmarking Hub39.7%†44.0%
DTBenchEpoch AI Benchmarking Hub84.8%†92.3%
ForecastBenchForecastBench64.6%–
Coding
SWE-bench Verified (Epoch)Epoch AI Benchmarking Hub62.3%†77.3%
SciCodeSciCode–49.5%
WeirdMLWeirdML52.4%†–
GSO-BenchGSO-Bench8.8%†–
Arena CodingArena (LMArena)14601523
Show all 127 benchmarks
MetricPublishero3Qwen3.7 (max)
Coding
Arena WebDevArena (LMArena)–1515
LiveBench 1.0 CodingLiveBench–74.2%
LiveCodeBenchVals AI83.9%†87.1%
SWE-bench (Vals)Vals AI–68.8%
Aider PolyglotAider polyglot leaderboard81.3%–
SWE-bench Verified (bash only)SWE-bench58.4%–
SWE-bench Verified (any scaffold)SWE-bench58.4%–
Code MigrationVals AI–13.1%
Vibe Code Bench v1.1Vals AI–47.7%
CadEvalEpoch AI Benchmarking Hub74.0%†–
ALE-BenchEpoch AI Benchmarking Hub933.5†1189.4
Terminal-Bench 4.0 (AA)Artificial Analysis–1.5%
Terminal-Bench 2.1 (AA)Artificial Analysis–74.5%
Startrise FrontendStartrise–63.6%
LiveCodeBench (AA)Artificial Analysis80.8%–
Agents & tools
GDPvalOpenAI30.8%†–
Arena AgentArena (LMArena)–-6.6
LiveBench Agentic CodingLiveBench–43.6%
Terminal-Bench HardArtificial Analysis37.1%50.8%
τ²-Bench Telecom (AA)Artificial Analysis80.7%94.7%
Terminal-Bench 2.1 (Vals)Vals AI–61.0%
BFCL OverallBerkeley Function Calling Leaderboard63.0%–
τ³-Banking (AA)Artificial Analysis–11.8%
ITBench SRE (AA)Artificial Analysis–42.5%
Analyst Agent (AA)Artificial Analysis–18.8%
Finance Agent v2Vals AI–47.8%
Harvey's Legal Agent Benchmark v1Vals AI–1.7%
Legal Research BenchVals AI–25.5%
Tax Agent BenchVals AI–15.8%
Terminal-Bench 2.0 (Vals)Vals AI–59.2%
DeepResearch BenchDeepResearch Bench45.2%†–
METR Time HorizonsMETR63.6%–
GBAEvalEpoch AI Benchmarking Hub–0.4%
AutomationBenchArtificial Analysis–23.0%
GDP.pdf (AA)Artificial Analysis–8.6%
EnterpriseOps-GymArtificial Analysis–45.0%
AA-Briefcase v1.1Artificial Analysis–917
BrowseComp-PlusBrowseComp-Plus50.5%–
Maths
FrontierMath Tiers 1–3Epoch AI Benchmarking Hub33.3%†64.6%
FrontierMath Tier 4Epoch AI Benchmarking Hub–34.1%
OTIS Mock AIMEEpoch AI Benchmarking Hub83.9%†95.6%
MATH Level 5Epoch AI Benchmarking Hub97.8%†–
ProofBenchVals AI–26.0%
LiveBench MathematicsLiveBench–85.3%
AIME (Vals)Vals AI85.3%†–
MGSMVals AI91.8%†–
IMO 2025MathArena16.7%†–
Omni-MATH (HELM)HELM Capabilities71.4%–
MATH 500Vals AI94.6%†–
Arena MathsArena (LMArena)14481482
AIME 2025 (AA)Artificial Analysis88.3%–
Knowledge
SimpleQA VerifiedEpoch AI Benchmarking Hub49.4%†55.8%
LiveBench 1.0 Data AnalysisLiveBench–71.8%
MMLU-ProVals AI85.6%†89.3%
LegalBenchVals AI83.8%†84.9%
CorpFinVals AI59.7%†63.7%
TaxEvalVals AI74.6%†75.3%
MedQAVals AI96.1%†–
PRBench FinanceScale AI SEAL47.7%–
PRBench LegalScale AI SEAL48.6%–
MultiNRCScale AI SEAL45.5%†–
MMLU-Pro (HELM)HELM Capabilities85.9%–
Excel Modeling BenchmarkVals AI–57.0%
MedCodeVals AI47.3%†38.8%
MedScribeVals AI76.7%†79.4%
DrugDiscoveryBenchScale AI SEAL–29.3%†
EBR-benchEpoch AI Benchmarking Hub–9.5%
Instruction following
LiveBench LanguageLiveBench–79.7%
LiveBench Instruction FollowingLiveBench–74.0%
IFBenchArtificial Analysis71.4%80.5%
MultiChallengeScale AI SEAL56.6%†–
TutorBenchScale AI SEAL52.1%†–
IFEval (HELM)HELM Capabilities86.9%–
WildBench (HELM)HELM Capabilities86.1%–
Arena Instruction FollowingArena (LMArena)14031465
Human preference
Arena TextArena (LMArena)14321474
EQ-Bench 4EQ-Bench–1100
Arena Creative WritingArena (LMArena)13831437
Arena Multi-turnArena (LMArena)14201482
Arena Longer QueriesArena (LMArena)14111490
Lech Mazur Creative WritingLech Mazur83.9%†–
Multimodal
Arena VisionArena (LMArena)1214–
MMMU-ProArtificial Analysis70.1%–
VISTAScale AI SEAL50.1%†–
MMMU (validation)MMMU82.9%–
MMMU-Pro (official)MMMU76.4%–
MMMU-Pro (Vals)Vals AI80.4%†–
MortgageTaxVals AI65.7%†–
VTBScale AI SEAL13.7%–
GeoBenchGeoBench60.0%†–
VPCTEpoch AI Benchmarking Hub52.0%†–
Long context
Fiction.LiveBench 120kFiction.live100.0%†–
AA-LCR v1.1Artificial Analysis74.7%79.0%
MLCRArtificial Analysis–14.4%
Composite
Epoch Capabilities IndexEpoch AI Benchmarking Hub146.8154.1
LiveBench 1.0LiveBench–73.1%
AA Intelligence Index v4.3.2Artificial Analysis20.229.5
AA Progress Index v1Artificial Analysis258.3293.8
HELM Capabilities meanHELM Capabilities81.1%–
Safety & honesty
FORTRESSScale AI SEAL16.0%–
MASKScale AI SEAL84.5%†–
PropensityBenchScale AI SEAL10.5%–

Data as of 2026-10-29. Best configuration of each model; every score links to its source on the model pages.

What changed

  • Qwen3.7 (max): BenchLeader Index 60.8 → 60.3.
  • o3: 1 new result (AA Progress Index v1).
  • Qwen3.7 (max): 1 new result (AA Progress Index v1).
  • Qwen3.7 (max): cached input price moved from $0.33/M to $0.50/M (52% up).
  • Qwen3.7 (max): cost per task moved from $1.15/M to $0.93/M (19% down).
  • Qwen3.7 (max): 1 new result (AA-Briefcase v1.1); 1 score revision; cached input price moved from $0.50/M to $0.33/M (34% down).
  • Qwen3.7 (max): cached input price moved from $0.33/M to $0.50/M (52% up).
  • Qwen3.7 (max): 1 new result (Harvey's Legal Agent Benchmark v1); cached input price moved from $0.50/M to $0.33/M (34% down).
  • Qwen3.7 (max): cached input price moved from $0.33/M to $0.50/M (52% up).
  • Qwen3.7 (max): 1 new result (MLCR).

Rankings: Best LLM overall · Best LLM for agents · Best cheap LLMs

o3 vs Qwen3.7: questions

Is o3 better than Qwen3.7?
o3 and Qwen3.7 (max) are neck and neck on quality (61.0 vs 60.3, within the ±5.3 margin). The BenchLeader Index combines every independent quality benchmark; the two are within the margin of error as of 29 Oct 2026, so check the category scores for your use.
o3 vs Qwen3.7: which is cheaper, and will that change?
o3 is cheaper today: $3.50 against $3.75 per million tokens, blended at three input tokens per output token. No price change has been announced for either.
Is o3 or Qwen3.7 better for coding?
o3 scores higher in coding (62 vs 59 on the category index, where 50 is average). On Arena Coding, the top shared coding benchmark, it is 1460 for o3 against 1523 for Qwen3.7.
Which is faster, o3 or Qwen3.7?
Qwen3.7 streams faster (201 vs 151 output tokens per second, Artificial Analysis 7-day median).
Is o3 or Qwen3.7 better for agents and tool use?
o3 scores higher in agentic tasks (70 vs 49 on the category index, where 50 is average). On Terminal-Bench Hard, the top shared agents & tools benchmark, it is 37.1% for o3 against 50.8% for Qwen3.7.
More questions (4)
Which is better for long documents?
Qwen3.7 scores higher on long-context benchmarks (64 vs 62). Qwen3.7 accepts more context: 1,000,000 against 200,000 tokens for o3.
Which has lower latency?
o3 answers first: 5.6 s against 14.1 s to the first answer token, as Artificial Analysis measures it. Reasoning effort drives most of this: a higher setting thinks longer before it answers.
Do independent benchmarks agree on o3 vs Qwen3.7?
Across the 16 benchmarks both have, o3 leads 0, Qwen3.7 leads 16. Every overall index that rates both puts Qwen3.7 ahead.
When was Qwen3.7 released?
Qwen3.7 was released on 19 May 2026.