Hugging Face's logo

Qwen
/
Qwen3.6-35B-A3B

Image-Text-to-Text
Transformers
Safetensors
qwen3_5_moe
conversational
Eval Results
Model card Files
xet
 Community
8

Add community evaluation results for AIME_2026, GPQA, HLE, HMMT_FEB_2026, MMLU-PRO, SWE-BENCH_PRO, SWE-BENCH_VERIFIED, TERMINAL-BENCH-2.0

#3
by nielsr HF Staff - opened
base: refs/heads/main
←
from: refs/pr/3
Discussion Files changed
+57
-0

YAML Metadata Error:Invalid content in Eval Result file .eval_results/hle.yaml

Check out the documentation for more information.

Show details
Task ID "hle" does not match any task in dataset "cais/hle". Available: none

YAML Metadata Error:Invalid content in Eval Result file .eval_results/mmlu-pro.yaml

Check out the documentation for more information.

Show details
Task ID "mmlu_pro" does not match any task in dataset "TIGER-Lab/MMLU-Pro". Available: none
Files changed (8) hide show
  1. .eval_results/aime_2026.yaml +7 -0
  2. .eval_results/gpqa.yaml +7 -0
  3. .eval_results/hle.yaml +7 -0
  4. .eval_results/hmmt_feb_2026.yaml +7 -0
  5. .eval_results/mmlu-pro.yaml +7 -0
  6. .eval_results/swe-bench_pro.yaml +7 -0
  7. .eval_results/swe-bench_verified.yaml +7 -0
  8. .eval_results/terminal-bench-2.0.yaml +8 -0
.eval_results/aime_2026.yaml ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ - dataset:
2
+ id: MathArena/aime_2026
3
+ task_id: MathArena/aime_2026
4
+ value: 92.7
5
+ source:
6
+ url: https://huggingface.co/Qwen/Qwen3.6-35B-A3B
7
+ name: Model Card
.eval_results/gpqa.yaml ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ - dataset:
2
+ id: Idavidrein/gpqa
3
+ task_id: diamond
4
+ value: 86
5
+ source:
6
+ url: https://huggingface.co/Qwen/Qwen3.6-35B-A3B
7
+ name: Model Card
.eval_results/hle.yaml ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ - dataset:
2
+ id: cais/hle
3
+ task_id: hle
4
+ value: 21.4
5
+ source:
6
+ url: https://huggingface.co/Qwen/Qwen3.6-35B-A3B
7
+ name: Model Card
.eval_results/hmmt_feb_2026.yaml ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ - dataset:
2
+ id: MathArena/hmmt_feb_2026
3
+ task_id: MathArena/hmmt_feb_2026
4
+ value: 83.6
5
+ source:
6
+ url: https://huggingface.co/Qwen/Qwen3.6-35B-A3B
7
+ name: Model Card
.eval_results/mmlu-pro.yaml ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ - dataset:
2
+ id: TIGER-Lab/MMLU-Pro
3
+ task_id: mmlu_pro
4
+ value: 85.2
5
+ source:
6
+ url: https://huggingface.co/Qwen/Qwen3.6-35B-A3B
7
+ name: Model Card
.eval_results/swe-bench_pro.yaml ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ - dataset:
2
+ id: ScaleAI/SWE-bench_Pro
3
+ task_id: SWE_Bench_Pro
4
+ value: 49.5
5
+ source:
6
+ url: https://huggingface.co/Qwen/Qwen3.6-35B-A3B
7
+ name: Model Card
.eval_results/swe-bench_verified.yaml ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ - dataset:
2
+ id: SWE-bench/SWE-bench_Verified
3
+ task_id: swe_bench_%_resolved
4
+ value: 73.4
5
+ source:
6
+ url: https://huggingface.co/Qwen/Qwen3.6-35B-A3B
7
+ name: Model Card
.eval_results/terminal-bench-2.0.yaml ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ - dataset:
2
+ id: harborframework/terminal-bench-2.0
3
+ task_id: terminalbench_2
4
+ value: 51.5
5
+ source:
6
+ url: https://huggingface.co/Qwen/Qwen3.6-35B-A3B
7
+ name: Model Card
8
+ notes: Harbor/Terminus-2 harness; 3h timeout, 32 CPU/48 GB RAM; temp=1.0, top_p=0.95, top_k=20, max_tokens=80K, 256K ctx; avg of 5 runs.