GPT-5.6 Sol vs GPT-5.6 Terra

Change models
IndexAll categories, out of 100.
73.0 ±1.9 best
68.9 ±2.0
GapIndex points below the top.
Top
−4.1
CoverageIndex weight that has results.
100%
100%
SpeedOutput tokens per second.
64/s
66/s best
EloLMArena rating and rank.
1457 best
1449
ReleasedMonth of release.
2026-07
2026-07
Input / 1MUS dollars per 1M input tokens.
$4.40
$2.00 best
Output / 1MUS dollars per 1M output tokens.
$22.00
$12.00 best
Batch output / 1MBatch price per 1M output tokens.
$10.00
$6.00 best
1K chats2K tokens in, 500 out, each.
$19.80
$10.00 best
1K documents20K tokens in, 1K out, each.
$110.00
$52.00 best
1K agent tasks200K tokens in, 20K out, each.
$1,320.00
$640.00 best
ContextMaximum tokens in one request.
1.05M
1.05M
AgenticMulti-step tasks with tools.
71.9 best
68.2
CodingCode writing and repair.
70.4 best
68.4
ReasoningLogic problems and puzzles.
76.3 best
72.5
MultimodalTasks with images and text.
72.6 best
67.3
KnowledgeFacts and expert knowledge.
72.7 best
65.5
MultilingualTasks in many languages.
66.4 best
60.7
InstructionTasks with strict prompt rules.
64.5 best
56.4
MathMath problems.
75.1 best
72.8

Benchmarks

105 shared
Only GPT-5.6 Sol: 20Only GPT-5.6 Terra: 4
GPT-5.6 Sol
GPT-5.6 Terra
49.5% best13 / 222
42.9%34 / 222
84.0% best8 / 217
83.0%18 / 217
93.5% best17 / 217
93.3%19 / 217
32.3% best3 / 214
30.0%10 / 214
EuroEval PolishMultilingual
62.8% best11 / 209
59.0%24 / 209
100.0% best1 / 200
99.7%14 / 200
94.1% best5 / 199
92.5%18 / 199
EuroEval SwedishMultilingual
74.9% best5 / 195
70.6%9 / 195
EuroEval GermanMultilingual
63.6% best5 / 191
59.7%10 / 191
70.5% best5 / 182
65.4%16 / 182
EuroEval FrenchMultilingual
72.0% best7 / 178
68.9%10 / 178
EuroEval SpanishMultilingual
66.3% best6 / 176
62.1%12 / 176
EuroEval DutchMultilingual
68.7% best6 / 175
65.0%11 / 175
EuroEval ItalianMultilingual
70.1% best7 / 174
67.8%10 / 174
59.4% best8 / 164
46.8%31 / 164
87.0% best7 / 149
85.1%25 / 149
85.1%56 / 149
86.3% best51 / 149
72.7% best34 / 146
71.2%39 / 146
TaxEval v2Finance
74.8%29 / 143
76.2% best6 / 143
82.6%51 / 142
85.9% best25 / 142