Hugging Face's logo

deepseek-ai
/
DeepSeek-V4-Pro

Text Generation
Transformers
Safetensors
deepseek_v4
Eval Results
8-bit precision
fp8
Model card Files
xet
 Community
156

Add community evaluation results for GPQA, GSM8K, HLE, MMLU-PRO, SWE-BENCH_PRO, SWE-BENCH_VERIFIED, TERMINAL-BENCH-2.0

#110
by nielsr HF Staff - opened
base: refs/heads/main
←
from: refs/pr/110
Discussion Files changed
+49
-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 (7) hide show
  1. .eval_results/gpqa.yaml +7 -0
  2. .eval_results/gsm8k.yaml +7 -0
  3. .eval_results/hle.yaml +7 -0
  4. .eval_results/mmlu-pro.yaml +7 -0
  5. .eval_results/swe-bench_pro.yaml +7 -0
  6. .eval_results/swe-bench_verified.yaml +7 -0
  7. .eval_results/terminal-bench-2.0.yaml +7 -0
.eval_results/gpqa.yaml ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ - dataset:
2
+ id: Idavidrein/gpqa
3
+ task_id: diamond
4
+ value: 90.1
5
+ source:
6
+ url: https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro
7
+ name: Model Card
.eval_results/gsm8k.yaml ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ - dataset:
2
+ id: openai/gsm8k
3
+ task_id: gsm8k
4
+ value: 92.6
5
+ source:
6
+ url: https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro
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: 37.7
5
+ source:
6
+ url: https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro
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: 87.5
5
+ source:
6
+ url: https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro
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: 55.4
5
+ source:
6
+ url: https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro
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: 80.6
5
+ source:
6
+ url: https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro
7
+ name: Model Card
.eval_results/terminal-bench-2.0.yaml ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ - dataset:
2
+ id: harborframework/terminal-bench-2.0
3
+ task_id: terminalbench_2
4
+ value: 67.9
5
+ source:
6
+ url: https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro
7
+ name: Model Card