Navigate
Advertise here

GPT-6.1 Terra (low) vs GPT-6.2 Sol (medium)

GPT-6.2 Sol (medium) leads on average score with 9.5 vs 9.3. GPT-6.1 Terra (low) has the lower benchmark cost at $0.221 vs $0.446. GPT-6.2 Sol (medium) is faster at 5.79s vs 6.05s, with pass rates of 85.5% vs 92.8%.

Last updated at: 2026-11-17

Compared models

Rank
#43
Total Output Tokens
12,656
Response Time (avg)
6.05s
Total Cost
$0.221
Rank
#35
Total Output Tokens
12,916
Response Time (avg)
5.79s
Total Cost
$0.446
Recommended model GPT-6.1 Terra (low)

Its score stays close to the best score here (9.3 vs 9.5), while costing about 2.0x less than GPT-6.2 Sol (medium).

Detailed comparison

Metric GPT-6.1 Terra GPT-6.1 Terra low Release: 2026-10-26 GPT-6.2 Sol GPT-6.2 Sol medium Release: 2026-11-17
Score 9.3 9.5
Rank #43 #35
Reliability 10.0 10.0
Consistency 9.7 9.4
Attempts 69/69 69/69
Tests Correct
Attempt pass rate 85.5% 92.8%
Flaky tests 1 2
Total Runs 69 69
Cost per result 1.162 2.230
Total Cost $0.221 $0.446
Input Price $1.000 / 1M $2.000 / 1M
Output Price $5.000 / 1M $10.000 / 1M
Cache Read Price $0.050 / 1M $0.100 / 1M
Cache Write Price $1.250 / 1M $2.500 / 1M
Total Input Tokens 157,463 158,328
Output Tokens 4,879 5,303
Reasoning Tokens 7,777 7,613
Response Time (avg) 6.05s 5.79s
Response Time (max) 43.50s 45.16s
Response Time (total) 139.21s 133.22s
Parameters ~1T total (~60B active) ~2T total (~150B active)
Availability Closed Closed

Cache prices apply to input tokens. Reads reuse cached prompts; writes store them and can cost extra. Output tokens use the output price.

Model generation showcase

Hamster playing table tennis

Prompt: Create a detailed SVG illustration of a hamster playing table tennis.

#43 GPT-6.1 Terra

low
Cost
$0.011
Time
24.9s
Tokens
2,238 tok

#35 GPT-6.2 Sol

medium
Cost
$0.040
Time
44.6s
Tokens
4,044 tok

Top Models by Score

Score vs Total Cost

Response Time (avg)

Score vs Response Time (avg)

Total Output Tokens

Score vs Total Output Tokens

Category Breakdown

Coding Score Consistency Attempt pass rate Flaky tests Tests Correct Response Time (avg) Input Tokens Output Tokens Reasoning Tokens
GPT-6.1 Terra 10.0 10.0 100.0% 0 3.51s 7,302 393 938
GPT-6.2 Sol 8.4 7.4 88.9% 1 3.36s 7,302 383 1,346

Switch Comparison Pair