Enter opens the highlighted result. Esc closes.

GPT-4o (2024-05-13) vs Qwen2.5 72B Instruct

Qwen2.5 72B Instruct leads GPT-4o (2024-05-13) on the Artificial Analysis Intelligence Index, 7.7 to 7.3, and Qwen2.5 72B Instruct costs 37.5x less per output token ($0.40 vs $15.00 per million). Updated October 22, 2026; 38 benchmarks have a result for both.

Replace GPT-4o (2024-05-13) Replace Qwen2.5 72B Instruct
GPT-4o (2024-05-13)OpenAI
Coding
No data
Overall
27.1
Output $/M
$15.00
31
Qwen2.5 72B InstructQwen
Coding
No data
Overall
26.5
Output $/M
$0.40
7
vs boards won of 38 shared

GPT-4o (2024-05-13) or Qwen2.5 72B Instruct: which to pick

Neither model has a coding score yet, so the two cannot be ranked on coding.

Pick GPT-4o (2024-05-13) for a larger context window (128K against 33K tokens) and work measured by AA Intelligence Index or Humanity's Last Exam (Artificial Analysis run), where it leads.

Model AGPT-4o (2024-05-13)OpenAINot benchmarkedNo coding benchmarkNo cost per solved taskModel BQwen2.5 72B InstructQwenNot benchmarkedNo coding benchmarkNo cost per solved task
Shared results
38
GPT-4o (2024-05-13) only
6
Qwen2.5 72B Instruct only
15
Like-for-like categories
7 of 9

Only benchmarks that tested both models count toward a pick; a result only one model has is shown but not compared.

Which one for your work

Each card is decided by one number both models carry. Where only one has it, the card says so and makes no call.

At a glance

Coding index
GPT-4o (2024-05-13) not benchmarked, Qwen2.5 72B Instruct not benchmarked.
Widest category
Agentic work, 10.5 points apart on average over 2 shared benchmarks.
Widest single gap
BALROG: GPT-4o (2024-05-13) 32.3% against Qwen2.5 72B Instruct 16.2%, 16.1 points apart on a 0 to 100 scale.
Output price
GPT-4o (2024-05-13) $15.00 against Qwen2.5 72B Instruct $0.40 per million output tokens, 37.5x apart.
Context window
GPT-4o (2024-05-13) takes 128K tokens, Qwen2.5 72B Instruct 33K.

Benchmark by benchmark

First the score: boards each model leads, per category, where both have a result. Then every board, a category to a fold; bars are each result on a 0 to 100 scale, so compare the two in a row, not one row with another.

Boards won, where both have a result
CategoryGPT-4o (2024-05-13)BarsQwen2.5 72B InstructTies
Coding30
Intelligence01
Agentic work20
Reasoning42
Math13
Knowledge51
General160
All shared boards317
CodingLike-for-likeSix of these boards feed the Vibe Coding Index30
Coding benchmarks for GPT-4o (2024-05-13) and Qwen2.5 72B Instruct
BenchmarkGPT-4o (2024-05-13)Qwen2.5 72B InstructLeader
AA Coding Index24.2Not measuredOnly GPT-4o (2024-05-13) measured
LiveCodeBench (Artificial Analysis run)33.4%27.6%GPT-4o (2024-05-13)
Terminal-Bench Hard (Artificial Analysis run)Not measured4.5%Only Qwen2.5 72B Instruct measured
WeirdMLNot measured16.0%Only Qwen2.5 72B Instruct measured
LMArena Text: coding12971292GPT-4o (2024-05-13)
LMArena Text: software and IT12971292GPT-4o (2024-05-13)
Neither model has a result on the other 37 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index01
Intelligence benchmarks for GPT-4o (2024-05-13) and Qwen2.5 72B Instruct
BenchmarkGPT-4o (2024-05-13)Qwen2.5 72B InstructLeader
AA Intelligence Index7.37.7Qwen2.5 72B Instruct
Epoch Capabilities IndexNot measured129.0Only Qwen2.5 72B Instruct measured
Agentic workLike-for-likePublic boards, shown as published, kept out of the index20
Agentic work benchmarks for GPT-4o (2024-05-13) and Qwen2.5 72B Instruct
BenchmarkGPT-4o (2024-05-13)Qwen2.5 72B InstructLeader
τ²-Bench TelecomNot measured34.5%Only Qwen2.5 72B Instruct measured
METR time horizons40.8%35.8%GPT-4o (2024-05-13)
BALROG32.3%16.2%GPT-4o (2024-05-13)
TheAgentCompanyNot measured5.7%Only Qwen2.5 72B Instruct measured
Neither model has a result on the other 38 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index42
Reasoning benchmarks for GPT-4o (2024-05-13) and Qwen2.5 72B Instruct
BenchmarkGPT-4o (2024-05-13)Qwen2.5 72B InstructLeader
GPQA Diamond50.2%Not measuredOnly GPT-4o (2024-05-13) measured
GPQA Diamond (Artificial Analysis run)52.6%49.1%GPT-4o (2024-05-13)
Humanity's Last Exam (Artificial Analysis run)1.8%3.6%Qwen2.5 72B Instruct
GPQA Diamond (Epoch AI run)48.9%49.1%Qwen2.5 72B Instruct
BIG-Bench HardNot measured79.8%Only Qwen2.5 72B Instruct measured
LMArena Text: hard prompts12811271GPT-4o (2024-05-13)
LMArena Text: expert12501245GPT-4o (2024-05-13)
LMArena Text: hard prompts in English12931279GPT-4o (2024-05-13)
Neither model has a result on the other 15 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index13
Math benchmarks for GPT-4o (2024-05-13) and Qwen2.5 72B Instruct
BenchmarkGPT-4o (2024-05-13)Qwen2.5 72B InstructLeader
AA Math IndexNot measured14.0Only Qwen2.5 72B Instruct measured
AIME 2025 (Artificial Analysis run)Not measured14.0%Only Qwen2.5 72B Instruct measured
OTIS Mock AIME6.3%8.1%Qwen2.5 72B Instruct
MATH level 551.0%63.2%Qwen2.5 72B Instruct
LMArena Text: math12841283GPT-4o (2024-05-13)
LMArena Text: mathematical work12841290Qwen2.5 72B Instruct
Neither model has a result on the other 8 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index51
Knowledge benchmarks for GPT-4o (2024-05-13) and Qwen2.5 72B Instruct
BenchmarkGPT-4o (2024-05-13)Qwen2.5 72B InstructLeader
MMLU Pro (Artificial Analysis run)74.0%72.0%GPT-4o (2024-05-13)
MMLU84.2%85.3%Qwen2.5 72B Instruct
AI2 Reasoning ChallengeNot measured94.5%Only Qwen2.5 72B Instruct measured
LMArena Text: science12951275GPT-4o (2024-05-13)
LMArena Text: medicine and healthcare12781258GPT-4o (2024-05-13)
LMArena Text: legal and government13141288GPT-4o (2024-05-13)
LMArena Text: business and finance12621253GPT-4o (2024-05-13)
Neither model has a result on the other 13 boards here
Web designNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Web design benchmarks for GPT-4o (2024-05-13) and Qwen2.5 72B Instruct
BenchmarkGPT-4o (2024-05-13)Qwen2.5 72B InstructLeader
Neither model has a result on 9 boards here
GeneralLike-for-likePublic boards, shown as published, kept out of the index160
General benchmarks for GPT-4o (2024-05-13) and Qwen2.5 72B Instruct
BenchmarkGPT-4o (2024-05-13)Qwen2.5 72B InstructLeader
IFBenchNot measured36.9%Only Qwen2.5 72B Instruct measured
DTBenchNot measured62.9%Only Qwen2.5 72B Instruct measured
LMCANot measured13.4%Only Qwen2.5 72B Instruct measured
HellaSwagNot measured84.8%Only Qwen2.5 72B Instruct measured
WinoGrandeNot measured82.3%Only Qwen2.5 72B Instruct measured
PIQANot measured82.6%Only Qwen2.5 72B Instruct measured
LMArena Text13001269GPT-4o (2024-05-13)
LMArena Text: instruction following12781254GPT-4o (2024-05-13)
LMArena Text: creative writing12911221GPT-4o (2024-05-13)
LMArena Vision1137Not measuredOnly GPT-4o (2024-05-13) measured
LMArena Text: English13121283GPT-4o (2024-05-13)
LMArena Text: non-English12831252GPT-4o (2024-05-13)
LMArena Text: Chinese12771273GPT-4o (2024-05-13)
LMArena Text: German12831234GPT-4o (2024-05-13)
LMArena Text: Japanese12571180GPT-4o (2024-05-13)
LMArena Text: Korean12341188GPT-4o (2024-05-13)
LMArena Text: French13041280GPT-4o (2024-05-13)
LMArena Text: Spanish12921255GPT-4o (2024-05-13)
LMArena Text: Russian12851264GPT-4o (2024-05-13)
LMArena Text: Polish1365Not measuredOnly GPT-4o (2024-05-13) measured
LMArena Text: multi-turn13021272GPT-4o (2024-05-13)
LMArena Text: longer queries12881281GPT-4o (2024-05-13)
LMArena Text: writing and language12981247GPT-4o (2024-05-13)
LMArena Text: entertainment and media12891211GPT-4o (2024-05-13)
LMArena Vision: English1147Not measuredOnly GPT-4o (2024-05-13) measured
LMArena Vision: Chinese1132Not measuredOnly GPT-4o (2024-05-13) measured
Neither model has a result on the other 22 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for GPT-4o (2024-05-13) and Qwen2.5 72B Instruct
BenchmarkGPT-4o (2024-05-13)Qwen2.5 72B InstructLeader
Neither model has a result on 5 boards here

What each workload costs

Three fixed token mixes at each model's listed price, so per-token rates become a bill.

Chat turn

1K input + 500 output tokens

GPT-4o (2024-05-13)$0.013Fits in one request
Qwen2.5 72B Instruct$0.0006Fits in one request

Qwen2.5 72B Instruct costs less

Repository review

50K input + 3K output tokens

GPT-4o (2024-05-13)$0.295Fits in one request
Qwen2.5 72B Instruct$0.019Exceeds the context window

Qwen2.5 72B Instruct costs less

Agent loop

200K input + 10K output tokens

GPT-4o (2024-05-13)$1.15Exceeds the context window
Qwen2.5 72B Instruct$0.076Exceeds the context window

Qwen2.5 72B Instruct costs less

Listed OpenRouter rates, without cache or batch discounts. A workload that does not fit a model's context window would need splitting.

Specification differences

The leading value in a row is marked; a row with a missing value names no leader. Our two rows are marked in red.

Specifications of GPT-4o (2024-05-13) and Qwen2.5 72B Instruct
SpecificationOpenAI GPT-4o (2024-05-13)Qwen2.5 72B Instruct
MakerOpenAIQwen
WeightsNo public weights listedOpen weights
ReleasedMay 13, 2024September 19, 2024
Context window128K33K
Input $/Mtok$5.00$0.36
Output $/Mtok$15.00$0.40
Coding indexNot benchmarkedNot benchmarked
Independent measurements behind it00
Cost per solved taskNot computableNot computable
SourceOpenRouter listingOpenRouter listing

Questions

Is GPT-4o (2024-05-13) better than Qwen2.5 72B Instruct for coding?

Neither model has a coding score yet, so the two cannot be ranked on coding. Pick GPT-4o (2024-05-13) for a larger context window (128K against 33K tokens) and work measured by AA Intelligence Index or Humanity's Last Exam (Artificial Analysis run), where it leads.

Which is cheaper, GPT-4o (2024-05-13) or Qwen2.5 72B Instruct?

GPT-4o (2024-05-13) costs $5.00 per million input tokens and $15.00 per million output tokens; Qwen2.5 72B Instruct costs $0.36 and $0.40. Cost per solved task is known for neither of them.

Which has the bigger context window, GPT-4o (2024-05-13) or Qwen2.5 72B Instruct?

GPT-4o (2024-05-13), with 128K tokens against 33K.

How many benchmarks is the GPT-4o (2024-05-13) vs Qwen2.5 72B Instruct comparison based on?

38 benchmarks have a result for both models as of October 22, 2026. GPT-4o (2024-05-13)'s coding index rests on 0 independent benchmarks and Qwen2.5 72B Instruct's on 0. Where only one model has a result, the page says so instead of naming a winner.

Compare next