SENTIENT WEEKLY
LLM

DeepSeek V4 Pro 0813 (Reasoning, Max Effort)

Overall Score
36.0
Released Aug 2026
Benchmark Scores
Reasoning
—
Coding
68.8
Math
—
Creative writing
—
Instruction following
—
Multimodal
—
Standard Benchmarks
aa_terminalbench_v2_1aa_terminalbench_v2_1
0.8
Measured 2026-09-26 · source
aa_ifbenchaa_ifbench
0.7
Measured 2026-08-12 · source
aa_gpqaaa_gpqa
0.9
Measured 2026-09-26 · source
aa_hleaa_hle
0.4
Measured 2026-09-26 · source
aa_scicodeaa_scicode
0.5
Measured 2026-09-26 · source
aa_tau_bankingaa_tau_banking
0.4
Measured 2026-09-26 · source
aa_terminalbench_hardaa_terminalbench_hard
0.4
Measured 2026-08-12 · source
aa_tau2aa_tau2
0.9
Measured 2026-08-12 · source
aa_lcraa_lcr
0.8
Measured 2026-09-26 · source
Price
$1.74/M
Paid
Context
1M
Speed
79.85 t/s
1083ms TTFT
Compare this model →

Discussion

0 comments

Sign in to join the conversation.

Be the first to comment.