Model comparison

GPT-5.6 Terra vs Qwen2.5 72B Instruct

GPT-5.6 Terra is the stronger model overall, scoring 59.2 to 31.9 on the Noometry Index. Qwen2.5 72B Instruct costs 1.8× less per token, which makes it the better buy when GPT-5.6 Terra's lead doesn't matter for your workload.

Last verified October 10, 2026. 24 shared benchmarks.

GPT-5.6 Terra OpenAI

59.2

Rank #17 Confirmed

Qwen2.5 72B Instruct

Alibaba (Qwen)

31.9

Rank #267 Confirmed

Summary

They share 24 benchmarks with published results for both. GPT-5.6 Terra scores higher in 9 categories and Qwen2.5 72B Instruct in 0 categories; 9 gaps are clear of the uncertainty.
The widest gap is in math, where GPT-5.6 Terra leads 81.6 to 19.3.
The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 99.7% for GPT-5.6 Terra and 8.1% for Qwen2.5 72B Instruct.
Qwen2.5 72B Instruct is cheaper at $1.40 / $5.60 per million input/output tokens, against $2 / $12 for GPT-5.6 Terra.
GPT-5.6 Terra accepts more context: 1.05M tokens versus 131K.
Qwen2.5 72B Instruct has downloadable open weights; the other is API-only.

Side by side

GPT-5.6 Terra and Qwen2.5 72B Instruct specifications
	GPT-5.6 Terra	Qwen2.5 72B Instruct
Provider	OpenAI	Alibaba (Qwen)
Noometry Index	59.2	31.9
Released	2026-07-09	2024-09
Weights	Proprietary	Open
Context window	1.05M	131K
Max output	128K	8K
Input $ / M tokens	$2	$1.40
Output $ / M tokens	$12	$5.60
Results tracked	52	43

Sponsored placements are available on pages like this one. Advertise on Noometry

Category by category

Coding GPT-5.6 Terra leads

GPT-5.6 Terra: 57.7 (#19), Qwen2.5 72B Instruct: 33.2 (#260)

Coding benchmarks
Benchmark	GPT-5.6 Terra	Qwen2.5 72B Instruct
WeirdML	78.3%	16%
LMArena Coding	1484	1292
DeepSWE	69.6%	—
FrontierCode	41.3%	—
CursorBench	41.3%	—
LMArena WebDev	1522	—
SciCode	55%	—
BigCodeBench Instruct	—	45.8%
BigCodeBench Complete	—	55.9%
ALE-Bench	1,951	—

Agentic & Tool Use GPT-5.6 Terra leads

GPT-5.6 Terra: 40.1 (#25), Qwen2.5 72B Instruct: 22.1 (#133)

Agentic & Tool Use benchmarks
Benchmark	GPT-5.6 Terra	Qwen2.5 72B Instruct
BALROG	53.2%	16.2%
APEX-Agents	58.2%	—
TheAgentCompany	—	5.7%
GDP.pdf	24.7%	—
METR Time Horizons	—	35.8%
Vending-Bench 2	7,343	—

Reasoning GPT-5.6 Terra leads

GPT-5.6 Terra: 60.7 (#21), Qwen2.5 72B Instruct: 22.3 (#199)

Reasoning benchmarks
Benchmark	GPT-5.6 Terra	Qwen2.5 72B Instruct
LMArena Hard Prompts	1468	1271
DTBench	93.3%	62.9%
LMCA	55%	13.4%
Epoch Capabilities Index	159.62	129
ARC-AGI-2	83.9%	—
SimpleBench	48.9%	—
Kagi LLM Benchmark	51.3%	—
NYT Connections (extended)	78.4%	—
ARC-AGI-1	96.5%	—
CritPt	30%	—
Chess Puzzles	54%	—
Mystery Game Puzzles	35%	—
Surface Evolver Bench	83.8%	—
BIG-Bench Hard	—	79.8%
ForecastBench	—	57.5
HellaSwag	—	84.8%
PIQA	—	82.6%
WinoGrande	—	82.3%

Math GPT-5.6 Terra leads

GPT-5.6 Terra: 81.6 (#12), Qwen2.5 72B Instruct: 19.3 (#287)

Math benchmarks
Benchmark	GPT-5.6 Terra	Qwen2.5 72B Instruct
OTIS Mock AIME 2024-2025	99.7%	8.1%
LMArena Math	1466	1283
FrontierMath (Tiers 1-3)	86%	—
FrontierMath Tier 4	70.7%	—
ProofBench	74%	—
Omni-MATH	—	33%
MATH Level 5	—	63.2%

Knowledge GPT-5.6 Terra leads

GPT-5.6 Terra: 61.2 (#30), Qwen2.5 72B Instruct: 27.0 (#253)

Knowledge benchmarks
Benchmark	GPT-5.6 Terra	Qwen2.5 72B Instruct
GPQA Diamond	93.3%	49.1%
LMArena Expert	1492	1245
SimpleQA Verified	43.2%	—
MMLU-Pro	—	63.1%
Confabulations	—	19.1%
GPQA (HELM)	—	42.6%
ARC (AI2) Challenge	—	94.5%
MMLU	—	85.3%
TriviaQA	—	71.9%

Multimodal Not comparable

GPT-5.6 Terra: 47.3 (#11), Qwen2.5 72B Instruct: —

Multimodal benchmarks
Benchmark	GPT-5.6 Terra	Qwen2.5 72B Instruct
LMArena Vision	1271	—
Blueprint-Bench 2	30.8%	—
Furniture Assembly	54.2%	—
LMArena Document	1472	—

Multilingual GPT-5.6 Terra leads

GPT-5.6 Terra: 54.4 (#44), Qwen2.5 72B Instruct: 41.0 (#213)

Multilingual benchmarks
Benchmark	GPT-5.6 Terra	Qwen2.5 72B Instruct
LMArena Non-English	1439	1252
LMArena Chinese	1513	1272
LMArena French	1471	1280
LMArena German	1460	1234
LMArena Japanese	1457	1180
LMArena Korean	1425	1188
LMArena Russian	1450	1264
LMArena Spanish	1448	1256

Instruction Following GPT-5.6 Terra leads

GPT-5.6 Terra: 76.4 (#40), Qwen2.5 72B Instruct: 65.5 (#221)

Instruction Following benchmarks
Benchmark	GPT-5.6 Terra	Qwen2.5 72B Instruct
LMArena Instruction Following	1454	1254
IFEval	—	80.6%

Long Context GPT-5.6 Terra leads

GPT-5.6 Terra: 44.4 (#68), Qwen2.5 72B Instruct: 38.9 (#188)

Long Context benchmarks
Benchmark	GPT-5.6 Terra	Qwen2.5 72B Instruct
LMArena Longer Query	1451	1282

Writing & Preference GPT-5.6 Terra leads

GPT-5.6 Terra: 70.2 (#23), Qwen2.5 72B Instruct: 46.7 (#215)

Writing & Preference benchmarks
Benchmark	GPT-5.6 Terra	Qwen2.5 72B Instruct
LMArena Text	1447	1269
LMArena Creative Writing	1410	1221
LMArena Multi-Turn	1449	1272
EQ-Bench Creative Writing	1855	—
WildBench	—	80.2%
EQ-Bench 4	1234	—

Frequently asked questions

Is GPT-5.6 Terra better than Qwen2.5 72B Instruct?

Which is cheaper, GPT-5.6 Terra or Qwen2.5 72B Instruct?

Qwen2.5 72B Instruct is cheaper. It lists at $1.40 per million input tokens and $5.60 per million output tokens; GPT-5.6 Terra lists at $2 and $12.

Is GPT-5.6 Terra or Qwen2.5 72B Instruct better for coding?

GPT-5.6 Terra scores higher on coding benchmarks: 57.7 versus 33.2 in the Noometry coding category.

Which has the bigger context window?

GPT-5.6 Terra does, with 1.05M tokens against 131K.

How many benchmarks do GPT-5.6 Terra and Qwen2.5 72B Instruct share?

24 benchmarks have published results for both models. GPT-5.6 Terra has 52 scored results on Noometry and Qwen2.5 72B Instruct has 43.