SYSTEMevaluerBench v1.0
TOTAL EVALS114 TESTS
MODELS TESTED10 MODELS
ACTIVE VIEWMATRIX
MODEL BENCHMARK HEATMAP
SYS-MTRX PASS
FAIL
UNTESTED
| MODEL / RUN | CODING | CONSTRAINTS | FORMATTING | KNOWLEDGE | LOGIC | QUALITY-ASSURANCE | CODING-COMPLEX | VISUAL-DEMO | ||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 10 RUNS | TypeScript Async Error Handling coding-ts-async-error | Math without Digits constraint-no-digits | Explain ML without Tech Words constraint-no-tech-words | Strict JSON Boolean Response format-json-boolean | Cellular Respiration knowledge-cellular-respiration | ESP32 GPIO Operations knowledge-esp32-gpio | 3D Printing Filament Characteristics knowledge-filament-types | TCP vs UDP Networking knowledge-tcp-udp | Misleading Server Math logic-misleading-servers | Sequential Race Logic logic-race-order | E-Commerce Cart QA qa-cart-edge-cases | Cyberpunk System Monitor Dashboard visual-cyberpunk-dashboard | Tango Logic Puzzle: Fire & Ice visual-tango-fire-ice | Standalone Tic-Tac-Toe Web App visual-tictactoe-game | ||||||||
Qwen3.6-35B-A3B-GGUF-UD-Q6_K_XL 52.46 t/s79% PASS | ||||||||||||||||||||||
Qwen3.6-27B-GGUF 11.74 t/s79% PASS | ||||||||||||||||||||||
Qwen3.5-35B-A3B-GGUF 52.78 t/s71% PASS | ||||||||||||||||||||||
gemma-4-26B-A4B-it-GGUF-UD-Q4_K_XL 43.77 t/s71% PASS | ||||||||||||||||||||||
Qwen3-Coder-Next-GGUF 50.14 t/s64% PASS | ||||||||||||||||||||||
Skyfall-31B-v4.2-GGUF-Q8_0 6.61 t/s57% PASS | ||||||||||||||||||||||
gpt-oss-20b-mxfp4-GGUF 74.38 t/s50% PASS | ||||||||||||||||||||||
LFM2.5-8B-A1B-GGUF-Q4_K_M 153.62 t/s29% PASS | ||||||||||||||||||||||
Qwen3.8-27B-GGUF-Q4-K-M 12.39 t/s0% PASS | —N/A | —N/A | —N/A | —N/A | —N/A | —N/A | —N/A | —N/A | —N/A | —N/A | —N/A | —N/A | —N/A | |||||||||
Qwen3.8-27B-GGUF-Q4_K_M 11.53 t/s0% PASS | —N/A | —N/A | —N/A | —N/A | —N/A | —N/A | —N/A | —N/A | —N/A | —N/A | —N/A | —N/A | —N/A | |||||||||
Eval Name
EVAL DETAILSModel / RunLoading reasoning...
EV-COMPARE
SIDE-BY-SIDE RUN COMPARATOR
GENERATION SPEED (AVG)
-- t/svs-- t/s
0 t/sTIME TO FIRST TOKEN (AVG)
-- msvs-- ms
0 msPASS RATE (%)
--%vs--%
0%INDIVIDUAL EVAL BENCHMARK COMPARISONS
0 EVALS ALIGNEDLATEST EVALInvalid Date
OVERALL TPS52.46
OVERALL TTFT361.15 ms
PASS RATE79%11 / 14 Passed
AVG GENERATION SPEED52.46 t/sTokens per second
AVG TIME TO FIRST TOKEN361.15 msTTFT Latency
TOTAL OUTPUT TOKENS49915Generated across evals
FILTER EVALS: