GPT-5.6 Terra vs GPT-6.1 Terra

Change models
IndexAll categories, out of 100.
68.9 ±2.0
77.1 ±3.8 best
GapIndex points below the top.
−8.2
Top
CoverageIndex weight that has results.
100% best
90%
SpeedOutput tokens per second.
66/s best
46/s
EloLMArena rating and rank.
1449
—
ReleasedMonth of release.
2026-07
2026-10
Input / 1MUS dollars per 1M input tokens.
$2.00
$1.00 best
Output / 1MUS dollars per 1M output tokens.
$12.00
$5.00 best
Batch output / 1MBatch price per 1M output tokens.
$6.00
$2.50 best
1K chats2K tokens in, 500 out, each.
$10.00
$4.50 best
1K documents20K tokens in, 1K out, each.
$52.00
$25.00 best
1K agent tasks200K tokens in, 20K out, each.
$640.00
$300.00 best
ContextMaximum tokens in one request.
1.05M
1.05M
AgenticMulti-step tasks with tools.
68.2
78.6 best
CodingCode writing and repair.
68.4
74.4 best
ReasoningLogic problems and puzzles.
72.5
81.3 best
MultimodalTasks with images and text.
67.3
73.2 best
KnowledgeFacts and expert knowledge.
65.5
70.5 best
MultilingualTasks in many languages.
60.7
—
InstructionTasks with strict prompt rules.
56.4
—
MathMath problems.
72.8
76.9 best

Benchmarks

33 shared
Only GPT-5.6 Terra: 76Only GPT-6.1 Terra: 17
GPT-5.6 Terra
GPT-6.1 Terra
42.9%34 / 222
46.2% best24 / 222
83.0% best18 / 217
82.7%23 / 217
93.3%19 / 217
94.3% best10 / 217
30.0% best10 / 214
28.0%16 / 214
99.7%14 / 200
100.0% best1 / 200
46.8%31 / 164
47.6% best28 / 164
74.6%44 / 123
84.0% best19 / 123
55.0%29 / 114
55.1% best28 / 114
80.7%17 / 113
84.7% best6 / 113
43.2%46 / 91
57.3% best21 / 91
86.0%13 / 90
90.9% best5 / 90
41.3% best30 / 90
26.0%62 / 90
30.0% best34 / 82
17.1%58 / 82
79.3%15 / 80
82.3% best4 / 80
90.6% best11 / 80
88.7%20 / 80
35.0%23 / 80
74.0% best4 / 80
70.7%17 / 72
92.7% best6 / 72
22.7%32 / 61
49.5% best11 / 61
−0.527 / 54
16.6 best4 / 54
−7.241 / 54
9.7 best11 / 54