GPT-5.1 vs Inkling-Small

Change models
GPT-5.1OpenAI
Inkling-SmallThinking Machines Lab
IndexAll categories, out of 100.
55.3 ±3.7 best
55.1 ±3.2
GapIndex points below the top.
Top
−0.2 · no clear gap
CoverageIndex weight that has results.
95%
95%
SpeedOutput tokens per second.
50/s
80/s best
EloLMArena rating and rank.
1422 best
1414
ReleasedMonth of release.
2025-11
2026-07
Input / 1MUS dollars per 1M input tokens.
$1.25
$0.45 best
Output / 1MUS dollars per 1M output tokens.
$10.00
$1.20 best
Batch output / 1MBatch price per 1M output tokens.
$5.00
—
1K chats2K tokens in, 500 out, each.
$7.50
$1.50 best
1K documents20K tokens in, 1K out, each.
$35.00
$10.20 best
1K agent tasks200K tokens in, 20K out, each.
$450.00
$114.00 best
ContextMaximum tokens in one request.
400K
524K best
AgenticMulti-step tasks with tools.
52.4
55.7 best
CodingCode writing and repair.
53.5
54.9 best
ReasoningLogic problems and puzzles.
56.4 best
55.7
MultimodalTasks with images and text.
58.4 best
54.7
KnowledgeFacts and expert knowledge.
57.2 best
52.0
MultilingualTasks in many languages.
—
—
InstructionTasks with strict prompt rules.
57.1
65.8 best
MathMath problems.
57.5 best
55.3

Benchmarks

22 shared
Only GPT-5.1: 22Only Inkling-Small: 42
GPT-5.1
Inkling-Small
28.5%87 / 222
33.3% best70 / 222
80.0% best43 / 217
75.7%92 / 217
87.6%61 / 217
88.5% best53 / 217
4.9%84 / 214
8.3% best74 / 214
88.6%67 / 200
90.0% best62 / 200
87.3%58 / 199
89.5% best43 / 199
37.7% best62 / 164
31.8%74 / 164
85.7% best20 / 149
83.0%62 / 149
TaxEval v2Finance
74.9%26 / 143
75.5% best18 / 143
86.5% best22 / 142
85.9%25 / 142
86.6% best41 / 135
83.6%55 / 135
MMLU ProKnowledge
86.4% best42 / 135
85.6%55 / 135
16.3%85 / 133
31.2% best60 / 133
CorpFin v2Finance
63.8%39 / 131
69.6% best6 / 131
24.6% best85 / 123
19.1%95 / 123
75.5% best48 / 113
74.0%61 / 113
MedScribeHealthcare
88.1% best14 / 109
84.1%38 / 109
MedCodeHealthcare
52.7% best13 / 106
37.9%74 / 106
61.4%60 / 97
62.3% best55 / 97
48.0% best35 / 91
19.1%79 / 91