Cost · Speed · Votes
Model leaderboard
Every generated entry across the coding and writing arenas, aggregated per model variant: community votes, output volume, estimated cost per task, and measured generation time. Click a column to sort.
| Model | |||||
|---|---|---|---|---|---|
| Fable 5 · low | 0 | 32 | ~10,365 | $0.52 | 20m 18s |
| Fable 5 · medium | 0 | 9 | ~11,468 | $0.57 | 25m 22s |
| Fable 5 · high | 0 | 8 | ~13,021 | $0.65 | 29m 52s |
| Fable 5 · xhigh | 0 | 9 | ~12,954 | $0.65 | 29m 51s |
| Fable 5 · max (post-ban) | 0 | 13 | ~16,332 | $0.82 | 39m 17s |
| Fable 5 (pre-ban) | 0 | 18 | ~15,339 | $0.77 | — |
| Opus 4.8 · low | 0 | 41 | ~13,565 | $0.34 | 2m 57s |
| Opus 4.8 · medium | 0 | 41 | ~14,466 | $0.36 | 4m 45s |
| Opus 4.8 · high | 0 | 41 | ~16,457 | $0.41 | 13m 56s |
| Opus 4.8 · xhigh | 0 | 41 | ~16,156 | $0.40 | 6m 33s |
| Opus 4.8 · max | 0 | 40 | ~16,891 | $0.42 | — |
| Sonnet 4.6 · low | 0 | 40 | ~9,603 | $0.14 | — |
| Sonnet 4.6 · medium | 0 | 40 | ~10,308 | $0.15 | — |
| Sonnet 4.6 · high | 0 | 40 | ~11,062 | $0.17 | — |
| Sonnet 4.6 · max | 0 | 40 | ~11,290 | $0.17 | — |
| Sonnet 5 · low | 0 | 18 | ~4,843 | $0.07 | 12m 12s |
| Sonnet 5 · medium | 0 | 13 | ~4,634 | $0.07 | 12m 18s |
| Sonnet 5 · high | 0 | 17 | ~5,208 | $0.08 | 12m 55s |
| Sonnet 5 · xhigh | 0 | 14 | ~5,328 | $0.08 | 12m 09s |
| Sonnet 5 · max | 0 | 15 | ~5,447 | $0.08 | 11m 28s |
| Haiku 4.5 | 0 | 51 | ~6,165 | $0.03 | 53s |
| GLM-5.2 | 0 | 18 | ~11,063 | — | — |
| GLM-5.2 · flash | 0 | 40 | ~12,940 | — | — |
| GPT-5.5 | 0 | 18 | ~6,325 | $0.06 | — |
| Gemini 3 Flash | 0 | 40 | ~7,137 | $0.02 | — |
| Kimi K2.7 Code | 0 | 4 | ~7,204 | $0.03 | — |
| Qwen3.7 Plus | 0 | 40 | ~7,373 | $0.01 | — |
| DeepSeek V4 Flash | 0 | 38 | ~14,925 | $0.00 | — |
| MiniMax M3 | 0 | 8 | ~2,602 | $0.00 | — |
| Kimi K2.6 | 0 | 40 | ~11,664 | $0.05 | — |
| Qwen3.7 Max | 0 | 38 | ~8,066 | $0.01 | — |
| DeepSeek V4 Pro | 0 | 5 | ~15,733 | $0.00 | — |
| MiniMax M2.7 | 0 | 40 | ~10,658 | $0.01 | — |
| GPT-5.5 · low | 0 | 5 | ~5,160 | $0.05 | — |
| GPT-5.5 · medium | 0 | 5 | ~6,090 | $0.06 | — |
| GPT-5.5 · high | 0 | 5 | ~8,021 | $0.08 | — |
| GPT-5.5 · xhigh | 0 | 5 | ~9,780 | $0.10 | — |
| Mistral Large 2512 | 0 | 7 | ~10,741 | $0.02 | — |
| Mistral Medium 3.5 | 0 | 7 | ~9,149 | $0.02 | — |
| Mistral Medium 3 (2508) | 0 | 4 | ~15,215 | $0.03 | — |
| Mistral Medium (2505) | 0 | 4 | ~9,898 | $0.02 | — |
| Mistral Small 2603 | 0 | 16 | ~7,700 | $0.02 | — |
| Mistral Small 2506 | 0 | 15 | ~6,475 | $0.01 | — |
| Codestral 2508 | 0 | 6 | ~7,891 | $0.02 | — |
| Devstral 2512 | 0 | 7 | ~9,202 | $0.02 | — |
| Magistral Medium · reasoning | 0 | 4 | ~6,677 | $0.01 | — |
| Magistral Medium · no-reason | 0 | 13 | ~8,675 | $0.02 | — |
| Magistral Small · reasoning | 0 | 12 | ~6,466 | $0.01 | — |
| Magistral Small · no-reason | 0 | 13 | ~6,342 | $0.01 | — |
| Ministral 14B | 0 | 8 | ~11,822 | $0.02 | — |
| Ministral 8B | 0 | 8 | ~10,571 | $0.02 | — |
| Ministral 3B | 0 | 33 | ~11,676 | $0.02 | — |
| Mistral Nemo | 0 | 37 | ~1,708 | $0.00 | — |
Token counts are estimated from artifact file size (chars ÷ 4). Cost = estimated output tokens × the model's published per-1M output price; input and reasoning tokens aren't counted, so true cost is higher — especially at high thinking effort. Generation time is wall-clock and only recorded for runs generated after 2026-07-02; it includes queue and throttling waits. Votes come from the public community tally. This page compares like-for-like one-shot generations, not lab benchmarks.