AgMoDB
ModelsAgentsOrchestratorsEvalsCompositesVisualizeIndustry
AgMoDB by @mistakeknot
All Models

Qwen2 Instruct 72B

June 7, 2024Last synced Nov 5, 2026, 12:19 AM

Blended Price

Free/M

Input Price

Free/M

Output Price

Free/M

Speed

—

TTFT

—

Benchmark Scores

Intelligence Index
—
Coding Index
—
Math Index
—
MMLU Pro
62.2 / 100
GPQA Diamond
37.1 / 100
HLE
3.7 / 100
LiveCodeBench
15.9 / 100
SciCode
— / 100
MATH-500
70.1 / 100
AIME
14.7 / 30
AIME 2025
— / 30
IFBench
— / 100
LCR
— / 100
Terminal-Bench Hard
— / 100
τ²-Bench
— / 100

Performance Radar

Qwen2 Instruct 72B
Field Average

Hidden, no data: AgMoBench Overall, AgMoBench Coding, AgMoBench Math, AgMoBench Agentic, AgMoBench Robustness, Output Speed

* Shared benchmarks shown in their place: GPQA Diamond, HLE

External Benchmarks

AlpacaEval 2.0 LCalpacaeval
38.1 / 100
AlpacaEval 2.0 Rawalpacaeval
29.9 / 100
AA-Omniscience AccuracyPredicted
40.7 / 100
AA-Omniscience Hallucination RatePredicted
94.0 / 100
Aider PolyglotPredicted
12.4 / 100
AIME 2025Predicted
0.1 / 30
ARC-AGI-1Predicted
0.9 / 100
ARC-AGI-1 Cost per TaskPredicted
0.0
ARC-AGI-2Predicted
0.7 / 100
ARC-AGI-2 Cost per TaskPredicted
0.0
BFCL (Berkeley Function Calling)Predicted
51.1
BigCodeBench CompletePredicted
54.2 / 100
BigCodeBench InstructPredicted
44.4 / 100
AA Intelligence Index (Matrix)Predicted
65.3
AA Long Context Reasoning (Matrix)Predicted
69.7
AIME 2024Predicted
27.4
AIME 2025 (Matrix)Predicted
13.2
Arena-Hard AutoPredicted
57.9
BrowseCompPredicted
58.8
BRUMO 2025Predicted
70.3
CMIMC 2025Predicted
84.1
CritPtPredicted
0.1
GPQA Diamond (Matrix)Predicted
45.2
GSM8KPredicted
71.3
HLE (Matrix)Predicted
63.1
HMMT Feb 2025Predicted
25.5
HMMT Nov 2025Predicted
88.1
HumanEvalPredicted
59.4
IFBench (Matrix)Predicted
26.0
IFEvalPredicted
69.5
IMO 2025Predicted
9.1
LiveCodeBench (Matrix)Predicted
33.0
MATH-500 (Matrix)Predicted
88.3
MathArena Apex 2025Predicted
0.6
MMLUPredicted
72.3
MMLU-Pro (Matrix)Predicted
64.0
MMMU-ProPredicted
82.2
MRCR v2Predicted
73.6
OSWorld (Unversioned Matrix Import)Predicted
32.9 / 100
SimpleQAPredicted
18.0
SMT 2025Predicted
66.8
SWE-bench ProPredicted
27.6
Tau-Bench Telecom (Matrix)Predicted
94.7
Terminal-Bench 2.0Predicted
20.2
Terminal-Bench 1.0Predicted
11.0
USAMO 2025Predicted
3.9
Video-MMUPredicted
85.9
browsecompPredicted
69.4
BullshitBenchPredicted
59.2 / 100
Aider PolyglotPredicted
0.0
Apex AgentsPredicted
2.2
Arc Agi 2Predicted
0.0
BALROGPredicted
0.0
BIG-Bench HardPredicted
3.0
BoolQPredicted
0.9
CAD-EvalPredicted
8.8
Chess PuzzlesPredicted
0.1
CyBenchPredicted
0.1
DeepResearchBenchPredicted
56.3
FictionLiveBenchPredicted
0.4
GdpvalPredicted
0.1
GeoBenchPredicted
0.0
GSM8K (Epoch)Predicted
10.8
GSOPredicted
0.0
HellaSwagPredicted
41.0
HlePredicted
0.2
Lech Mazur WritingPredicted
6.7
OTIS Mock AIME 2024–2025Predicted
0.1
PIQAPredicted
0.9
PosttrainbenchPredicted
0.0
SimpleQA Verified (Epoch)Predicted
0.4
TriviaQAPredicted
2.7
VPCTPredicted
0.3
WinoGrandePredicted
0.8
FrontierMathPredicted
51.4 / 100
GAIA Level 1Predicted
19.7
GAIA Level 2Predicted
5.5
GAIA Level 3Predicted
0.0
GAIAPredicted
12.1 / 100
IFBenchPredicted
0.2 / 100
LCRPredicted
0.0 / 100
LegalBenchPredicted
78.9 / 100
LiveBench CodingPredicted
68.9 / 100
LiveBench Data AnalysisPredicted
40.7 / 100
LiveBench LanguagePredicted
56.6 / 100
LiveBench MathPredicted
59.9 / 100
LiveBench OverallPredicted
44.7 / 100
LiveBench ReasoningPredicted
37.1 / 100
LongBench v2 EasyPredicted
38.1
LongBench v2 HardPredicted
37.2
LongBench v2Predicted
29.9 / 100
MathVistaPredicted
51.2 / 100
MedQA (USMLE)Predicted
62.6
MLE-bench (Original)Predicted
13.4 / 100
MMMUPredicted
57.4 / 100
MMTU Table UnderstandingPredicted
45.1 / 100
MT-BenchPredicted
7.9 / 10
NoLiMa (NIAH)Predicted
90.8 / 100
OCRBench v2Predicted
75.9 / 100
RE-BenchPredicted
0.1
SimpleBenchPredicted
19.5 / 100
simpleqaPredicted
17.7
SWE-bench LitePredicted
9.0 / 100
SWE-bench VerifiedPredicted
22.5 / 100
τ²-BenchPredicted
0.0 / 100
tau-bench RetailPredicted
74.1 / 100
Terminal-Bench HardPredicted
0.0 / 100
Vectara Factual ConsistencyPredicted
92.8 / 100
Vectara Hallucination RatePredicted
7.2 / 100
WebArenaPredicted
6.0 / 100
WeirdMLPredicted
15.0 / 100
Arena ELO: Creative Writingchatbot_arena
1222.0
Chatbot Arena ELOchatbot_arena
1203.0
METR Time Horizonsepoch_ai
0.3
The Agent Companyepoch_ai
0.0
Open LLM Averageopen_llm_leaderboard
43.6 / 100
Open LLM: BBHopen_llm_leaderboard
69.8 / 100
Open LLM: GPQAopen_llm_leaderboard
37.2 / 100
Open LLM: IFEvalopen_llm_leaderboard
79.9 / 100
Open LLM: MATH Level 5open_llm_leaderboard
41.8 / 100
Open LLM: MMLU-PROopen_llm_leaderboard
54.0 / 100
Open LLM: MUSRopen_llm_leaderboard
45.6 / 100
WeirdMLweirdml
11.3 / 100
WildBenchwildbench
46.4

How Qwen2 Instruct 72B Compares

Axes

Filters

$0.00 – $67.5
≥ 1.4

Providers

ai2ai21-labsalibabaanthropicarceeawsazurebaidu
openai
zai
meta
nvidia
xai
upstage
deepseek
alibaba
mistral
nous-research
aws
google
anthropic
xiaomi
stepfun
kimi
reflection
minimax
azure
inclusionai
reka-ai
cohere
bytedance_seed
inception
tencent
thinking-machines
Bubble size = Context Window
8191.00
2000000.00
Compare with other models