Navigate
Advertise here

Compared models

MiniMax M2.7 (medium) vs Kimi K2.5 (medium) vs GLM 5 (medium) vs Gemini 3.1 Flash Lite Preview (medium) benchmark comparison: GLM 5 (medium) leads on Score with 7.2. MiniMax M2.7 (medium) leads on Reliability with 10.0. Gemini 3.1 Flash Lite Preview (medium) has the lowest Total Cost at $0.158. Gemini 3.1 Flash Lite Preview (medium) is fastest at 6.78s.

Last updated at: 2026-10-01

Compared models

Rank
#298
Total Output Tokens
174,351
Response Time (avg)
50.32s
Total Cost
$0.202
Rank
#205
Total Output Tokens
241,096
Response Time (avg)
125.76s
Total Cost
$0.603
Rank
#146
Total Output Tokens
138,257
Response Time (avg)
39.05s
Total Cost
$0.360
Rank
#155
Total Output Tokens
59,534
Response Time (avg)
6.78s
Total Cost
$0.158
Recommended model Gemini 3.1 Flash Lite Preview (medium)

Its score stays close to the best score here (7.0 vs 7.2), while costing about 2.5x less than the other models in this comparison.

Detailed comparison

Metric MiniMax M2.7 MiniMax M2.7 medium Release: 2026-03-18 Kimi K2.5 Kimi K2.5 medium Release: 2026-01-27 GLM 5 GLM 5 medium Release: 2026-02-12 Gemini 3.1 Flash Lite Preview Gemini 3.1 Flash Lite Preview medium Release: 2026-03-03
Score 5.0 6.4 7.2 7.0
Rank #298 #205 #146 #155
Reliability 10.0 9.6 10.0 10.0
Consistency 6.4 7.1 7.9 9.9
Attempts 69/69 69/69 66/69 69/69
Tests Correct
Attempt pass rate 44.9% 60.9% 76.8% 60.9%
Flaky tests 10 8 5 0
Total Runs 69 69 66 69
Cost per result 5.279 6.085 2.552 1.124
Total Cost $0.202 $0.603 $0.360 $0.158
Input Price $0.210 / 1M $0.450 / 1M $0.600 / 1M $0.250 / 1M
Output Price $0.840 / 1M $2.250 / 1M $1.920 / 1M $1.500 / 1M
Total Input Tokens 277,130 292,271 212,440 272,221
Output Tokens 45,188 55,025 22,922 12,345
Reasoning Tokens 129,163 186,071 115,335 47,189
Response Time (avg) 50.32s 125.76s 39.05s 6.78s
Response Time (max) 198.82s 566.79s 110.70s 54.91s
Response Time (total) 1107.03s 2137.84s 546.68s 155.96s
Parameters 230B total (10B active) 1T total (32B active) 744B total (40B active) ~150B total (~10B active)
Availability Weights available Weights available Open source Closed

Model generation showcase

Hamster playing table tennis

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

#298 MiniMax M2.7

medium
Cost
$0.022
Time
22.8s
Tokens
9,250 tok

#205 MoonshotAI: Kimi K2.5

medium
Cost
$0.030
Time
58.6s
Tokens
8,683 tok

#146 GLM 5

medium
Cost
$0.005
Time
20.7s
Tokens
2,068 tok

#155 Gemini 3.1 Flash Lite Preview

medium
Cost
$0.003
Time
5.2s
Tokens
1,944 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
MiniMax M2.7 5.7 9.1 33.3% 0 101.89s 2,961 1,231 38,841
Kimi K2.5 6.1 4.6 66.7% 2 217.49s 6,935 5,705 74,693
GLM 5 10.0 10.0 100.0% 0 74.30s 7,254 2,997 52,930
Gemini 3.1 Flash Lite Preview 5.5 10.0 33.3% 0 4.09s 8,126 461 8,597

Quick Compare

Switch Comparison Pair