Compare

Four models, one page

Pick the models you are actually choosing between. Every row is scaled within itself, so a bar means something next to its neighbours and nothing across rows.

Slot 1

Slot 2

Slot 3

Slot 4

Specification	Ling-2.6-flashInclusionAI	Claude Opus 5Anthropic
Released	Apr 21, 2026	Jul 24, 2026
Context window	262K	1M
Max output	33K	128K
Input / 1M	$0.01	$5
Output / 1M	$0.03	$25
Cost per task	$0.001	$2.25
Arena Elo	—	1,393
Serving providers	1	5
Parameters	Undisclosed	Undisclosed
Licence	Proprietary	Proprietary
Capabilities	Tool use	Reasoning Tool use Vision

Metrics side by side

Each row is scaled to the largest value in that row — bars compare within a row, never across rows

Ling-2.6-flash
Claude Opus 5

Intelligence Index
Ling-2.6-flash
14.2
Claude Opus 5
63.1
Coding Index
Ling-2.6-flash
25.3
Claude Opus 5
78.0
Agentic Index
Ling-2.6-flash
2.3
Claude Opus 5
59.2
Output speed
Ling-2.6-flash
86 t/s
Claude Opus 5
87 t/s
Context window
Ling-2.6-flash
262K
Claude Opus 5
1M
Latency · lower is better
Ling-2.6-flash
614ms
Claude Opus 5
1.12s
Blended price / 1M · lower is better
Ling-2.6-flash
$0.015
Claude Opus 5
$10
Cost per task · lower is better
Ling-2.6-flash
$0.001
Claude Opus 5
$2.25

Rows marked “lower is better” still draw a longer bar for a larger number — read the value, not just the length. Arena Elo is in the specification table above instead: it has no meaningful zero, so a bar would flatten the gaps.

View as table

Metric	Ling-2.6-flash	Claude Opus 5
Intelligence Index	14.2	63.1
Coding Index	25.3	78.0
Agentic Index	2.3	59.2
Output speed	86 t/s	87 t/s
Context window	262K	1M
Latency · lower is better	614ms	1.12s
Blended price / 1M · lower is better	$0.015	$10
Cost per task · lower is better	$0.001	$2.25

Evaluation scores

Percentage correct on a common 0–100% scale

Ling-2.6-flash
Claude Opus 5

GPQA Diamond
Ling-2.6-flash
59.3%
Claude Opus 5
93.2%
Humanity's Last Exam
Ling-2.6-flash
6.3%
Claude Opus 5
54.9%
SciCode
Ling-2.6-flash
27.1%
Claude Opus 5
55.7%
τ²-bench
Ling-2.6-flash
86.0%
Claude Opus 5
42.1%
Terminal-Bench Hard
Ling-2.6-flash
21.2%
Claude Opus 5not measured
AA-LCR long context
Ling-2.6-flash
28.0%
Claude Opus 5
75.7%

A missing bar means that evaluation was not run for that model — it is not a zero.

View as table

Evaluation	Ling-2.6-flash	Claude Opus 5
GPQA Diamond	59.3%	93.2%
Humanity's Last Exam	6.3%	54.9%
SciCode	27.1%	55.7%
τ²-bench	86.0%	42.1%
Terminal-Bench Hard	21.2%	—
LiveCodeBench	—	—
AA-LCR long context	28.0%	75.7%
AIME 2025	—	—

Estimated from list pricing: 50K input tokens plus 80K output tokens for reasoning models (25K for non-reasoning).