SYNCING VERIFIED SOURCES

Loading ranking table…

Loading the latest published snapshot and its supporting evidence.

LiveBench Model Cost Efficiency | Rank.ai

RANK.AI DATA / Latest

LiveBench Model Cost Efficiency

Official LiveBench cost per successful task beside capability, token use, and release pricing for 2026-06-25.

Coverage: 45 entities
Confidence: 100%
Freshness: current
Export: CSV / JSON

PUBLIC VIEW / NO LOGINTrack this exact boardFilters and comparisons stay in the URL. Bookmark it, share it, or follow verified snapshot changes.

Follow changes

Watching publication Jun 25, 2026

LEADERBOARD

Current rankings

Metric: LiveBench cost per successful task

Find in tableEntity typeMovementConfidenceEvidence NRank rangeColumns

45of 45 rows

LiveBench Model Cost Efficiency current rankings
Rank	Entity	Signal	LiveBench cost per successful task	Confidence	N	Explain
01	DeepSeek V4 Flashmodel	Official LiveBench release: 2026-06-25.	$0.016	100%	7	Why this rank
02	Grok Build 0.1model	Official LiveBench release: 2026-06-25.	$0.024	100%	7	Why this rank
03	DeepSeek V4 Promodel	Official LiveBench release: 2026-06-25.	$0.050	100%	7	Why this rank
04	MiniMax M3model	Official LiveBench release: 2026-06-25.	$0.060	100%	7	Why this rank
05	Grok 4.3model	Official LiveBench release: 2026-06-25.	$0.061	100%	7	Why this rank
06	Gemini 3.5 Flash Lite Highmodel	Official LiveBench release: 2026-06-25.	$0.069	100%	7	Why this rank
07	GPT 5.4 Nano xHighmodel	Official LiveBench release: 2026-06-25.	$0.091	100%	7	Why this rank
08	Kimi K2.7 Codemodel	Official LiveBench release: 2026-06-25.	$0.100	100%	7	Why this rank
09	GPT 5.6 Luna xHighmodel	Official LiveBench release: 2026-06-25.	$0.123	100%	7	Why this rank
10	Grok 4.5model	Official LiveBench release: 2026-06-25.	$0.128	100%	7	Why this rank
11	Muse Spark 1.1 Highmodel	Official LiveBench release: 2026-06-25.	$0.138	100%	7	Why this rank
12	Kimi K2.6 Thinkingmodel	Official LiveBench release: 2026-06-25.	$0.169	100%	7	Why this rank
13	Qwen3.7 Maxmodel	Official LiveBench release: 2026-06-25.	$0.182	100%	7	Why this rank
14	GPT 5.2 Codexmodel	Official LiveBench release: 2026-06-25.	$0.187	100%	7	Why this rank
15	GLM 5.2model	Official LiveBench release: 2026-06-25.	$0.195	100%	7	Why this rank
16	Qwen3.6 27bmodel	Official LiveBench release: 2026-06-25.	$0.202	100%	7	Why this rank
17	GPT 5.6 Luna Maxmodel	Official LiveBench release: 2026-06-25.	$0.202	100%	7	Why this rank
18	GPT 5.6 Terra xHighmodel	Official LiveBench release: 2026-06-25.	$0.208	100%	7	Viewing why
19	GPT 5.5model	Official LiveBench release: 2026-06-25.	$0.212	100%	7	Why this rank
20	Qwen3.6 Plusmodel	Official LiveBench release: 2026-06-25.	$0.227	100%	7	Why this rank
21	GPT 5.2 2025 12 11 Highmodel	Official LiveBench release: 2026-06-25.	$0.234	100%	7	Why this rank
22	Muse Spark 1.1 xHighmodel	Official LiveBench release: 2026-06-25.	$0.234	100%	7	Why this rank
23	Gemini 3.6 Flash Highmodel	Official LiveBench release: 2026-06-25.	$0.235	100%	7	Why this rank
24	Gemini 3.5 Flash Highmodel	Official LiveBench release: 2026-06-25.	$0.249	100%	7	Why this rank
25	Gemini 3.1 Pro Preview Highmodel	Official LiveBench release: 2026-06-25.	$0.262	100%	7	Why this rank
26	Claude Sonnet 4 6 Thinking Auto Medium Effortmodel	Official LiveBench release: 2026-06-25.	$0.306	100%	7	Why this rank
27	GPT 5.4 Mini xHighmodel	Official LiveBench release: 2026-06-25.	$0.334	100%	7	Why this rank
28	Inkling xHighmodel	Official LiveBench release: 2026-06-25.	$0.343	100%	7	Why this rank
29	GPT 5.6 Sol xHighmodel	Official LiveBench release: 2026-06-25.	$0.355	100%	7	Why this rank
30	GPT 5.5 Highmodel	Official LiveBench release: 2026-06-25.	$0.367	100%	7	Why this rank
31	Claude Opus 5 High Effortmodel	Official LiveBench release: 2026-06-25.	$0.373	100%	7	Why this rank
32	Kimi K3model	Official LiveBench release: 2026-06-25.	$0.379	100%	7	Why this rank
33	GPT 5.4 xHighmodel	Official LiveBench release: 2026-06-25.	$0.387	100%	7	Why this rank
34	Claude Opus 4 6 Thinking Auto High Effortmodel	Official LiveBench release: 2026-06-25.	$0.404	100%	7	Why this rank
35	Claude Opus 5 xHigh Effortmodel	Official LiveBench release: 2026-06-25.	$0.487	100%	7	Why this rank
36	Claude Sonnet 5 xHigh Effortmodel	Official LiveBench release: 2026-06-25.	$0.492	100%	7	Why this rank
37	GPT 5.6 Terra Maxmodel	Official LiveBench release: 2026-06-25.	$0.497	100%	7	Why this rank
38	Claude Opus 4 7 xHigh Effortmodel	Official LiveBench release: 2026-06-25.	$0.528	100%	7	Why this rank
39	GPT 5.5 xHighmodel	Official LiveBench release: 2026-06-25.	$0.530	100%	7	Why this rank
40	GPT 5.6 Sol Maxmodel	Official LiveBench release: 2026-06-25.	$0.589	100%	7	Why this rank
41	Claude Opus 4 5 20251101 Thinking 64K High Effortmodel	Official LiveBench release: 2026-06-25.	$0.610	100%	7	Why this rank
42	Claude Opus 5 Max Effortmodel	Official LiveBench release: 2026-06-25.	$0.641	100%	7	Why this rank
43	Claude Opus 4 8 xHigh Effortmodel	Official LiveBench release: 2026-06-25.	$0.688	100%	7	Why this rank
44	Claude Fable 5 xHigh Effortmodel	Official LiveBench release: 2026-06-25.	$0.811	100%	7	Why this rank
45	Claude Fable 5 Max Effortmodel	Official LiveBench release: 2026-06-25.	$1.573	100%	7	Why this rank

HISTORICAL SERIES

LiveBench Model Cost Efficiency leader

Historical data is not available for this snapshot yet.

Some explanation inputs are unavailable Missing: publicFrozenEvidence, comparablePriorRanking.

Published rank: #18
Score: 0.208
Overall confidence: 100%
Coverage: 64%
Sample size: 7
As of: Jun 25, 2026, 11:59 PM UTC

SCORE CONSTRUCTION

Component ledger

7/11 evidenced

Components contributing to GPT 5.6 Terra xHigh's rank
Component	Value	Weight	Contribution	Evidence	Status
livebench average input tokens	—	0%	0	1	available
livebench average output tokens	—	0%	0	1	available
livebench cost per question usd	—	0%	0	1	available
livebench cost per successful task usd

livebench input price per million usd	—	0%	0	1	available

livebench output price per million usd	—	0%	0	1	available

livebench overall score	—	0%	0	1	available

metrics	Structured	Unavailable	—	0	unavailableno_public_frozen_evidence

rankingDirection	ascending	Unavailable	—	0	unavailableno_public_frozen_evidence

release	2026-06-25	Unavailable	—	0	unavailableno_public_frozen_evidence

sourceModelId	gpt-5.6-terra-xhigh	Unavailable	—	0	unavailableno_public_frozen_evidence

PRIMARY EVIDENCE

Source trail

7 public records

LiveBench average input tokenslivebench average input tokens · observed Jun 25, 2026, 11:59 PM UTC77,353 tokens100% confidence
Source
LiveBench official model benchmark
Grade
A
Freshness
fresh
Locator
{"formula":"(sum task cost / sum question count) / (overall score / 100)","costAsset":"https://livebench.ai/cost_2026_06_25.csv","scoreAsset":"https://livebench.ai/table_2026_06_25.csv","categoryAsset":"https://livebench.ai/categories_2026_06_25.json"}
Open primary evidence ↗
LiveBench average output tokenslivebench average output tokens · observed Jun 25, 2026, 11:59 PM UTC8,228 tokens100% confidence
Source
LiveBench official model benchmark
Grade
A
Freshness
fresh
Locator
{"formula":"(sum task cost / sum question count) / (overall score / 100)","costAsset":"https://livebench.ai/cost_2026_06_25.csv","scoreAsset":"https://livebench.ai/table_2026_06_25.csv","categoryAsset":"https://livebench.ai/categories_2026_06_25.json"}
Open primary evidence ↗
LiveBench cost per questionlivebench cost per question usd · observed Jun 25, 2026, 11:59 PM UTC0.154 USD_per_question100% confidence
Source
LiveBench official model benchmark
Grade
A
Freshness
fresh
Locator
{"formula":"(sum task cost / sum question count) / (overall score / 100)","costAsset":"https://livebench.ai/cost_2026_06_25.csv","scoreAsset":"https://livebench.ai/table_2026_06_25.csv","categoryAsset":"https://livebench.ai/categories_2026_06_25.json"}
Open primary evidence ↗
LiveBench cost per successful tasklivebench cost per successful task usd · observed Jun 25, 2026, 11:59 PM UTC0.208 USD_per_successful_task100% confidence
Source
LiveBench official model benchmark
Grade
A
Freshness
fresh
Locator
{"formula":"(sum task cost / sum question count) / (overall score / 100)","costAsset":"https://livebench.ai/cost_2026_06_25.csv","scoreAsset":"https://livebench.ai/table_2026_06_25.csv","categoryAsset":"https://livebench.ai/categories_2026_06_25.json"}
Open primary evidence ↗
LiveBench input pricelivebench input price per million usd · observed Jun 25, 2026, 11:59 PM UTC2.5 USD_per_million_tokens100% confidence
Source
LiveBench official model benchmark
Grade
A
Freshness
fresh
Locator
{"formula":"(sum task cost / sum question count) / (overall score / 100)","costAsset":"https://livebench.ai/cost_2026_06_25.csv","scoreAsset":"https://livebench.ai/table_2026_06_25.csv","categoryAsset":"https://livebench.ai/categories_2026_06_25.json"}
Open primary evidence ↗
LiveBench output pricelivebench output price per million usd · observed Jun 25, 2026, 11:59 PM UTC15 USD_per_million_tokens100% confidence
Source
LiveBench official model benchmark
Grade
A
Freshness
fresh
Locator
{"formula":"(sum task cost / sum question count) / (overall score / 100)","costAsset":"https://livebench.ai/cost_2026_06_25.csv","scoreAsset":"https://livebench.ai/table_2026_06_25.csv","categoryAsset":"https://livebench.ai/categories_2026_06_25.json"}
Open primary evidence ↗
LiveBench overall scorelivebench overall score · observed Jun 25, 2026, 11:59 PM UTC74.252 percent100% confidence
Source
LiveBench official model benchmark
Grade
A
Freshness
fresh
Locator
{"formula":"(sum task cost / sum question count) / (overall score / 100)","costAsset":"https://livebench.ai/cost_2026_06_25.csv","scoreAsset":"https://livebench.ai/table_2026_06_25.csv","categoryAsset":"https://livebench.ai/categories_2026_06_25.json"}
Open primary evidence ↗