GPT-5.4 nano vs Ling 3.0 Flash

Change models
Ling 3.0 FlashInclusionAI
IndexAll categories, out of 100.
50.9 ±2.5
50.9 ±4.7
GapIndex points below the top.
Top
Top
CoverageIndex weight that has results.
100% best
85%
SpeedOutput tokens per second.
91/s best
73/s
EloLMArena rating and rank.
1372
—
ReleasedMonth of release.
2026-03
2026-07
Input / 1MUS dollars per 1M input tokens.
$0.20
$0.021 best
Output / 1MUS dollars per 1M output tokens.
$1.25
$0.063 best
Batch output / 1MBatch price per 1M output tokens.
$0.625
—
1K chats2K tokens in, 500 out, each.
$1.03
$0.074 best
1K documents20K tokens in, 1K out, each.
$5.25
$0.483 best
1K agent tasks200K tokens in, 20K out, each.
$65.00
$5.46 best
ContextMaximum tokens in one request.
400K best
262K
AgenticMulti-step tasks with tools.
50.5
53.5 best
CodingCode writing and repair.
53.7 best
50.0
ReasoningLogic problems and puzzles.
53.7 best
48.8
MultimodalTasks with images and text.
41.7
—
KnowledgeFacts and expert knowledge.
44.5
46.1 best
MultilingualTasks in many languages.
44.4
—
InstructionTasks with strict prompt rules.
61.3 best
58.6
MathMath problems.
55.9 best
54.5

Benchmarks

25 shared
Only GPT-5.4 nano: 49Only Ling 3.0 Flash: 18
GPT-5.4 nano
Ling 3.0 Flash
28.3% best90 / 222
23.7%102 / 222
76.7% best84 / 217
73.0%103 / 217
9.3% best69 / 214
1.7%109 / 214
81.7%93 / 199
85.5% best75 / 199
25.7% best102 / 164
18.2%140 / 164
77.9%105 / 149
79.7% best93 / 149
TaxEval v2Finance
67.4%107 / 143
70.6% best89 / 143
84.0%41 / 142
84.0%41 / 142
82.8%61 / 141
85.0% best53 / 141
77.5%76 / 135
84.8% best49 / 135
MMLU ProKnowledge
77.2%105 / 135
82.0% best80 / 135
22.4%79 / 133
22.4%79 / 133
CorpFin v2Finance
61.2%55 / 131
61.9% best49 / 131
26.1% best83 / 123
2.9%116 / 123
47.2% best64 / 114
42.0%80 / 114
MedScribeHealthcare
77.1%71 / 109
80.9% best54 / 109
MedCodeHealthcare
41.0% best59 / 106
32.3%89 / 106
6.3% best84 / 90
0.0%90 / 90
SWE-benchCoding
69.8% best64 / 87
65.2%72 / 87
38.2% best64 / 79
30.3%71 / 79