Gemini 4 Carbon vs GPT-6 Astra

Change models
IndexAll categories, out of 100.
82.7 ±5.1 best
78.0 ±1.9
GapIndex points below the top.
Top
−4.7 · no clear gap
CoverageIndex weight that has results.
80%
100% best
SpeedOutput tokens per second.
31/s
34/s best
EloLMArena rating and rank.
1538 best
1440
ReleasedMonth of release.
2026-10
2026-09
Input / 1MUS dollars per 1M input tokens.
$2.00 best
$10.00
Output / 1MUS dollars per 1M output tokens.
$10.00 best
$50.00
Batch output / 1MBatch price per 1M output tokens.
$5.00 best
$25.00
1K chats2K tokens in, 500 out, each.
$9.00 best
$45.00
1K documents20K tokens in, 1K out, each.
$50.00 best
$250.00
1K agent tasks200K tokens in, 20K out, each.
$600.00 best
$3,000.00
ContextMaximum tokens in one request.
1.05M
1.05M
AgenticMulti-step tasks with tools.
83.2 best
74.6
CodingCode writing and repair.
80.5 best
76.9
ReasoningLogic problems and puzzles.
83.9 best
83.8
MultimodalTasks with images and text.
—
71.2
KnowledgeFacts and expert knowledge.
79.5 best
78.5
MultilingualTasks in many languages.
—
73.6
InstructionTasks with strict prompt rules.
—
79.5
MathMath problems.
77.2
78.0 best

Benchmarks

35 shared
Only Gemini 4 Carbon: 4Only GPT-6 Astra: 103
Gemini 4 Carbon
GPT-6 Astra
79.3%52 / 217
80.7% best37 / 217
96.5% best1 / 217
95.8%3 / 217
100.0%1 / 200
100.0%1 / 200
58.3%9 / 164
61.6% best6 / 164
92.1%5 / 131
95.0% best1 / 131
97.5%5 / 126
97.5%5 / 126
89.1%9 / 123
89.6% best8 / 123
97.9% best3 / 122
97.5%5 / 122
98.5% best6 / 116
97.8%14 / 116
77.7% best2 / 91
75.6%4 / 91
Chess PuzzlesReasoning
78.0% best2 / 90
74.0%3 / 90
90.5%6 / 90
93.7% best2 / 90
55.8% best1 / 90
39.4%37 / 90
51.8% best1 / 82
20.7%52 / 82
73.0%5 / 80
84.0% best2 / 80
95.1%4 / 72
97.6% best3 / 72
63.1% best4 / 61
59.6%5 / 61
19.1 best2 / 54
14.85 / 54
18.4 best4 / 54
14.06 / 54
77.5%6 / 37
80.0% best3 / 37