Gemini 4 Argon vs GPT-5.6 Terra

Change models
IndexAll categories, out of 100.
78.5 ±4.3 best
68.9 ±2.0
GapIndex points below the top.
Top
−9.6
CoverageIndex weight that has results.
80%
100% best
SpeedOutput tokens per second.
28/s
66/s best
EloLMArena rating and rank.
1530 best
1449
ReleasedMonth of release.
2026-09
2026-07
Input / 1MUS dollars per 1M input tokens.
$2.00
$2.00
Output / 1MUS dollars per 1M output tokens.
$10.00 best
$12.00
Batch output / 1MBatch price per 1M output tokens.
$5.00 best
$6.00
1K chats2K tokens in, 500 out, each.
$9.00 best
$10.00
1K documents20K tokens in, 1K out, each.
$50.00 best
$52.00
1K agent tasks200K tokens in, 20K out, each.
$600.00 best
$640.00
ContextMaximum tokens in one request.
1.05M
1.05M
AgenticMulti-step tasks with tools.
77.3 best
68.2
CodingCode writing and repair.
76.7 best
68.4
ReasoningLogic problems and puzzles.
79.8 best
72.5
MultimodalTasks with images and text.
—
67.3
KnowledgeFacts and expert knowledge.
76.5 best
65.5
MultilingualTasks in many languages.
—
60.7
InstructionTasks with strict prompt rules.
—
56.4
MathMath problems.
75.9 best
72.8

Benchmarks

56 shared
Only Gemini 4 Argon: 30Only GPT-5.6 Terra: 53
Gemini 4 Argon
GPT-5.6 Terra
57.1% best4 / 222
42.9%34 / 222
79.7%45 / 217
83.0% best18 / 217
96.4% best2 / 217
93.3%19 / 217
27.1%17 / 214
30.0% best10 / 214
100.0% best1 / 200
99.7%14 / 200
48.3% best26 / 164
46.8%31 / 164
88.3% best3 / 149
85.1%25 / 149
56.2% best14 / 133
47.6%33 / 133
91.3% best7 / 131
83.9%17 / 131
98.5% best1 / 126
96.5%11 / 126
91.9% best3 / 123
74.6%44 / 123
97.1% best6 / 122
91.3%13 / 122
99.5% best1 / 116
98.3%8 / 116
61.8% best5 / 114
55.0%29 / 114
MedScribeHealthcare
87.4% best17 / 109
82.9%50 / 109
MedCodeHealthcare
58.8% best3 / 106
43.4%45 / 106
76.0% best3 / 91
43.2%46 / 91
Chess PuzzlesReasoning
59.0% best10 / 90
47.0%24 / 90
86.0%13 / 90
86.0%13 / 90
54.8% best5 / 90
41.3%30 / 90