Hugging Face's logo

moonshotai
/
Kimi-K2.6

Image-Text-to-Text
Transformers
Safetensors
kimi_k25
feature-extraction
compressed-tensors
conversational
custom_code
Eval Results
Model card Files
xet
 Community
7
bigeagle SaylorTwift HF Staff commited on
Commit
d9cb81b
·
1 Parent(s): 36d7872

Add evaluation results for HLE, GPQA, AIME, HMMT, SWE-Bench, and Terminal-Bench (#4)

Browse files

- Add evaluation results for HLE, GPQA, AIME, HMMT, SWE-Bench, and Terminal-Bench (64ed7450cf8801fae6fc24d6bea85e034393d974)


Co-authored-by: Nathan Habib <SaylorTwift@users.noreply.huggingface.co>

Files changed (8) hide show
  1. .eval_results/aime_2026.yaml +9 -0
  2. .eval_results/gpqa_diamond.yaml +9 -0
  3. .eval_results/hle.yaml +9 -0
  4. .eval_results/hle_with_tools.yaml +10 -0
  5. .eval_results/hmmt_feb_2026.yaml +9 -0
  6. .eval_results/swe_bench_pro.yaml +9 -0
  7. .eval_results/swe_bench_verified.yaml +9 -0
  8. .eval_results/terminal_bench_2.yaml +9 -0
.eval_results/aime_2026.yaml ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ - dataset:
2
+ id: MathArena/aime_2026
3
+ task_id: MathArena/aime_2026
4
+ value: 96.4
5
+ date: '2026-04-20'
6
+ source:
7
+ url: https://huggingface.co/moonshotai/Kimi-K2.6
8
+ name: Model Card
9
+ user: SaylorTwift
.eval_results/gpqa_diamond.yaml ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ - dataset:
2
+ id: Idavidrein/gpqa
3
+ task_id: diamond
4
+ value: 90.5
5
+ date: '2026-04-20'
6
+ source:
7
+ url: https://huggingface.co/moonshotai/Kimi-K2.6
8
+ name: Model Card
9
+ user: SaylorTwift
.eval_results/hle.yaml ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ - dataset:
2
+ id: cais/hle
3
+ task_id: hle
4
+ value: 34.7
5
+ date: '2026-04-20'
6
+ source:
7
+ url: https://huggingface.co/moonshotai/Kimi-K2.6
8
+ name: Model Card
9
+ user: SaylorTwift
.eval_results/hle_with_tools.yaml ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ - dataset:
2
+ id: cais/hle
3
+ task_id: hle
4
+ value: 54.0
5
+ date: '2026-04-20'
6
+ source:
7
+ url: https://huggingface.co/moonshotai/Kimi-K2.6
8
+ name: Model Card
9
+ user: SaylorTwift
10
+ notes: "With tools"
.eval_results/hmmt_feb_2026.yaml ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ - dataset:
2
+ id: MathArena/hmmt_feb_2026
3
+ task_id: MathArena/hmmt_feb_2026
4
+ value: 92.7
5
+ date: '2026-04-20'
6
+ source:
7
+ url: https://huggingface.co/moonshotai/Kimi-K2.6
8
+ name: Model Card
9
+ user: SaylorTwift
.eval_results/swe_bench_pro.yaml ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ - dataset:
2
+ id: ScaleAI/SWE-bench_Pro
3
+ task_id: SWE_Bench_Pro
4
+ value: 58.6
5
+ date: '2026-04-20'
6
+ source:
7
+ url: https://huggingface.co/moonshotai/Kimi-K2.6
8
+ name: Model Card
9
+ user: SaylorTwift
.eval_results/swe_bench_verified.yaml ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ - dataset:
2
+ id: SWE-bench/SWE-bench_Verified
3
+ task_id: swe_bench_%_resolved
4
+ value: 80.2
5
+ date: '2026-04-20'
6
+ source:
7
+ url: https://huggingface.co/moonshotai/Kimi-K2.6
8
+ name: Model Card
9
+ user: SaylorTwift
.eval_results/terminal_bench_2.yaml ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ - dataset:
2
+ id: harborframework/terminal-bench-2.0
3
+ task_id: terminalbench_2
4
+ value: 66.7
5
+ date: '2026-04-20'
6
+ source:
7
+ url: https://huggingface.co/moonshotai/Kimi-K2.6
8
+ name: Model Card
9
+ user: SaylorTwift