Navigate
AI BENCHY
Advertise here

Granite 4.1 8B vs gpt-oss-120b

Granite 4.1 8B leads on average score with 4.0 vs 3.7. Granite 4.1 8B has the lower benchmark cost at $0.007 vs $0.010. Granite 4.1 8B is faster at 1.45s vs 21.61s, with pass rates of 9.1% vs 33.3%.

Last updated at: 2026-07-28

Rank
#224
Total Output Tokens
5,996
Response Time (avg)
1.45s
Total Cost
$0.007
Rank
#229
Total Output Tokens
51,664
Response Time (avg)
21.61s
Total Cost
$0.010
Recommended model Granite 4.1 8B

It has the best score here (4.0), while responding about 14.9x faster than gpt-oss-120b.

Detailed comparison

Metric Granite 4.1 8B Granite 4.1 8B none Release: 2026-05-01 gpt-oss-120b gpt-oss-120b none Release: 2025-08-05 Free Available
Score 4.0 3.7
Rank #224 #229
Reliability 10.0 10.0
Consistency 10.0 7.8
Tests Correct
Attempt pass rate 9.1% 33.3%
Flaky tests 0 2
Total Runs 66 57
Cost per result 0.315 0.168
Total Cost $0.007 $0.010
Input Price $0.050 / 1M $0.037 / 1M
Output Price $0.100 / 1M $0.170 / 1M
Total Input Tokens 113,827 9,081
Output Tokens 5,996 51,664
Reasoning Tokens 0 0
Response Time (avg) 1.45s 21.61s
Response Time (max) 16.67s 113.71s
Response Time (total) 31.96s 345.79s

Model generation showcase

Hamster playing table tennis

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

#224 IBM: Granite 4.1 8B

none
Cost
$0.001
Time
3.2s
Tokens
491 tok

#229 gpt-oss-120b

none
No showcase result has been generated for this model yet.
Cost
$0.000
Time
-
Tokens
0 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
Granite 4.1 8B 4.5 10.0 0.0% 0 775ms 8,344 525 0
gpt-oss-120b 1.5 4.0 22.2% 1 9.57s 901 3,232 0

Quick Compare

Switch Comparison Pair