GPT-5.5 vs GPT-5.6 Terra

Change models
GPT-5.5OpenAI
IndexAll categories, out of 100.
69.1 ±2.5 best
68.9 ±2.0
GapIndex points below the top.
Top
−0.2 · no clear gap
CoverageIndex weight that has results.
95%
100% best
SpeedOutput tokens per second.
52/s
66/s best
EloLMArena rating and rank.
1466 best
1449
ReleasedMonth of release.
2026-04
2026-07
Input / 1MUS dollars per 1M input tokens.
$5.00
$2.00 best
Output / 1MUS dollars per 1M output tokens.
$30.00
$12.00 best
Batch output / 1MBatch price per 1M output tokens.
$15.00
$6.00 best
1K chats2K tokens in, 500 out, each.
$25.00
$10.00 best
1K documents20K tokens in, 1K out, each.
$130.00
$52.00 best
1K agent tasks200K tokens in, 20K out, each.
$1,600.00
$640.00 best
ContextMaximum tokens in one request.
1.05M
1.05M
AgenticMulti-step tasks with tools.
65.8
68.2 best
CodingCode writing and repair.
65.5
68.4 best
ReasoningLogic problems and puzzles.
74.1 best
72.5
MultimodalTasks with images and text.
66.8
67.3 best
KnowledgeFacts and expert knowledge.
70.4 best
65.5
MultilingualTasks in many languages.
—
60.7
InstructionTasks with strict prompt rules.
64.8 best
56.4
MathMath problems.
74.7 best
72.8

Benchmarks

78 shared
Only GPT-5.5: 34Only GPT-5.6 Terra: 31
GPT-5.5
GPT-5.6 Terra
45.8% best26 / 222
42.9%34 / 222
84.3% best7 / 217
83.0%18 / 217
94.0% best13 / 217
93.3%19 / 217
27.1%17 / 214
30.0% best10 / 214
100.0% best1 / 200
99.7%14 / 200
93.5% best8 / 199
92.5%18 / 199
58.0% best10 / 164
46.8%31 / 164
86.5% best13 / 149
85.1%25 / 149
98.0% best8 / 149
86.3%51 / 149
75.9% best16 / 146
71.2%39 / 146
TaxEval v2Finance
75.0%25 / 143
76.2% best6 / 143
85.3%33 / 142
85.9% best25 / 142
93.6% best8 / 141
92.9%12 / 141
93.2% best10 / 135
90.9%24 / 135
MMLU ProKnowledge
88.1% best21 / 135
86.7%39 / 135
42.5%44 / 133
47.6% best33 / 133
85.0% best13 / 131
83.9%17 / 131
CorpFin v2Finance
68.4% best9 / 131
65.3%28 / 131
95.0%19 / 126
96.5% best11 / 126
69.8%50 / 123
74.6% best44 / 123