DeepSeek V4 Flash 0731 vs GPT-5.6 Luna: Release Comparison

Name: Artificial Analysis Intelligence Index
Creator: Artificial Analysis
License: https://artificialanalysis.ai/docs/legal/Terms-of-Use.pdf

Comparison of the DeepSeek V4 Flash 0731 and GPT-5.6 Luna releases: 2 and 6 models respectively, each with different intelligence, performance, and pricing characteristics. Below is a comparison of the key metrics across all 8 models.

For intelligence, GPT-5.6 Luna scores highest: GPT-5.6 Luna (max) at 38, against DeepSeek V4 Flash Vision (Reasoning, Max Effort) at 35 for DeepSeek V4 Flash 0731.
For output speed, DeepSeek V4 Flash 0731 is fastest: DeepSeek V4 Flash Vision (Reasoning, Max Effort) at 213 t/s, against GPT-5.6 Luna (max) at 120 t/s for GPT-5.6 Luna.
For cost per task, GPT-5.6 Luna is cheapest: GPT-5.6 Luna (low) at $0.01, against DeepSeek V4 Flash 0731 (Reasoning, Max Effort) at $0.22 for DeepSeek V4 Flash 0731.

Releases compared

Intelligence

Artificial Analysis Intelligence Index

Artificial Analysis Intelligence Index v4.3 incorporates 10 evaluations: AA-Briefcase, GDPval-AA v2, AutomationBench-AA, Terminal-Bench v4.0, SciCode, Humanity's Last Exam, GDP.pdf, CritPt, AA-Omniscience, AA-LCR v1.1

Estimate (independent evaluation forthcoming)

Artificial Analysis Intelligence Index v4.3 includes: AA-Briefcase, GDPval-AA v2, AutomationBench-AA, Terminal-Bench v4.0, SciCode, Humanity's Last Exam, GDP.pdf, CritPt, AA-Omniscience, AA-LCR v1.1. See Intelligence Index methodology for further details, including a breakdown of each evaluation and how we run them.

Intelligence Index vs. Cost per Intelligence Index Task

Artificial Analysis Intelligence Index · Weighted average cost (USD) per Artificial Analysis Intelligence Index task

Most attractive quadrant

DeepSeek V4 Flash 0731

GPT-5.6 Luna

Pareto line

Weighted average cost per Intelligence Index task. Each evaluation’s cost is calculated from input, cache hit, cache write, reasoning, and answer token prices, divided by task count, and weighted by its Intelligence Index weight.

Cost

Cost per Intelligence Index Task

Weighted average cost (USD) per Artificial Analysis Intelligence Index task, segmented by token type. Lower is better

Speed & Latency

Output Speed

Output tokens per second · Higher is better

Tokens per second received while the model is generating tokens (ie. after first chunk has been received from the API for models which support streaming).

Figures represent performance of the model's first-party API (e.g. OpenAI for o1) or the median across providers where a first-party API is not available (e.g. Meta's Llama models).

Capability Scores

Capability Indices

Measures the performance of models on specific capabilities and industries

Finance & Accounting Index

Incorporates 7 evaluations: AA-Omniscience, GDPval-AA v2, AA-Briefcase, Humanity's Last Exam, AutomationBench-AA, AA-LCR v1.1, GDP.pdf · Higher is better

Strategy & Ops Index

Incorporates 6 evaluations: AA-Omniscience, GDPval-AA v2, AA-Briefcase, AutomationBench-AA, AA-LCR v1.1, GDP.pdf · Higher is better

Legal Index

Incorporates 7 evaluations: AA-Omniscience, GDPval-AA v2, AA-Briefcase, Humanity's Last Exam, AA-LCR v1.1, GDP.pdf, AutomationBench-AA · Higher is better

Healthcare & Medical Index

Incorporates 6 evaluations: AA-Omniscience, GDPval-AA v2, AA-Briefcase, MLCR-AA, Humanity's Last Exam, AutomationBench-AA · Higher is better

Engineering Index

Incorporates 6 evaluations: AA-Omniscience, Humanity's Last Exam, CritPt, GDPval-AA v2, AA-Briefcase, Terminal-Bench v4.0 · Higher is better

Economics Index

Incorporates 5 evaluations: AA-Omniscience, Humanity's Last Exam, GDPval-AA v2, AA-Briefcase, AA-LCR v1.1 · Higher is better

Further details


																												Input modality	Output modality	Weights			Provider Benchmarks
GPT-5.6 Luna (max)	OpenAI	38	-	-	-	-	36	43	$0.18	$0.2	$0.20	$1.20	$0.02	$320	41k	28k	154M	120	128.28s	128.28s	132.46s	355.87s	-	1M	Jul 2026	-	Yes	Supports: text and image	Supports: text	Not available	-		View
DeepSeek V4 Flash Vision (Reasoning, Max Effort)	DeepSeek	35	38	44	37	-	35	40	$0.31	$0.2	$0.44	$1.32	$0.014	$445	69k	46k	170M	213	1.15s	10.53s	12.88s	241.53s	284B 13B active at inference time	1M	Aug 2026	-	Yes	Supports: text and image	Supports: text	Not available	-		View
GPT-5.6 Luna (xhigh)	OpenAI	35	38	41	35	33	34	41	$0.09	$0.2	$0.20	$1.20	$0.02	$179	24k	15k	85M	117	52.08s	52.08s	56.37s	203.53s	-	1M	Jul 2026	-	Yes	Supports: text and image	Supports: text	Not available	-		View
DeepSeek V4 Flash 0731 (Reasoning, Max Effort)	DeepSeek	35	38	43	38	36	35	40	$0.22	$0.2	$0.44	$1.32	$0.014	$474	62k	45k	242M	213	1.30s	10.70s	13.05s	220.40s	284B 13B active at inference time	1M	Jul 2026	-	Yes	Supports: text	Supports: text	🤗	Mit	+12	View
GPT-5.6 Luna (high)	OpenAI	32	35	37	33	30	32	38	$0.04	$0.2	$0.20	$1.20	$0.02	$108	14k	7k	50M	103	8.68s	8.68s	13.52s	134.67s	-	1M	Jul 2026	-	Yes	Supports: text and image	Supports: text	Not available	-		View
GPT-5.6 Luna (medium)	OpenAI	25	28	29	28	25	27	32	$0.02	$0.2	$0.20	$1.20	$0.02	$44	4k	2k	18M	108	2.86s	2.86s	7.48s	42.35s	-	1M	Jul 2026	-	Yes	Supports: text and image	Supports: text	Not available	-		View
GPT-5.6 Luna (low)	OpenAI	22	24	23	25	21	23	29	$0.01	$0.2	$0.20	$1.20	$0.02	$27	3k	559	10M	102	2.21s	2.21s	7.11s	24.41s	-	1M	Jul 2026	-	Yes	Supports: text and image	Supports: text	Not available	-		View
GPT-5.6 Luna (Non-reasoning)	OpenAI	17	-	-	-	-	-	22	-	$0.2	$0.20	$1.20	$0.02	-	-	-	-	109	0.93s	0.93s	5.52s	-	-	1M	Jul 2026	-	No	Supports: text and image	Supports: text	Not available	-		View

DeepSeek V4 Flash 0731 vs GPT-5.6 Luna: Release Comparison

Intelligence

Artificial Analysis Intelligence Index

Artificial Analysis Intelligence Index

Intelligence Index vs. Cost per Intelligence Index Task

Cost per Intelligence Index Task

Artificial Analysis Intelligence Index

Cost

Cost per Intelligence Index Task

Cost per Intelligence Index Task

Speed & Latency

Output Speed

Output Speed

Model Performance Representation

Capability Scores

Capability Indices

Further details