o1 vs Trinity-Large-Thinking

Change models
o1OpenAI
IndexAll categories, out of 100.
44.3 ±4.1 best
43.8 ±7.2
GapIndex points below the top.
Top
−0.5 · no clear gap
CoverageIndex weight that has results.
95% best
75%
SpeedOutput tokens per second.
97/s
138/s best
EloLMArena rating and rank.
1366 best
1340
ReleasedMonth of release.
2024-12
2026-03
Input / 1MUS dollars per 1M input tokens.
$15.00
$0.25 best
Output / 1MUS dollars per 1M output tokens.
$60.00
$0.80 best
1K chats2K tokens in, 500 out, each.
$60.00
$0.90 best
1K documents20K tokens in, 1K out, each.
$360.00
$5.80 best
1K agent tasks200K tokens in, 20K out, each.
$4,200.00
$66.00 best
ContextMaximum tokens in one request.
200K
262K best
AgenticMulti-step tasks with tools.
45.1
45.7 best
CodingCode writing and repair.
30.9
47.9 best
ReasoningLogic problems and puzzles.
43.4 best
35.8
MultimodalTasks with images and text.
55.3
—
KnowledgeFacts and expert knowledge.
46.6 best
45.1
MultilingualTasks in many languages.
—
—
InstructionTasks with strict prompt rules.
51.1 best
39.7
MathMath problems.
43.4
—

Benchmarks

6 shared
Only o1: 23Only Trinity-Large-Thinking: 12
o1
Trinity-Large-Thinking
7.0%155 / 216
15.8% best119 / 216
65.0% best130 / 211
38.0%163 / 211
0.3%132 / 207
0.9% best119 / 207
74.7%115 / 193
75.2% best110 / 193
62.6%79 / 143
90.1% best38 / 143
70.3% best41 / 140
56.3%65 / 140