Battles
One published battle is one qualifying evaluation group. Pairwise comparisons are on the battle page. Repeated missing difficulty is not listed as a result.
155 battles. Newest published time first.
-
View Quality battle, Sep 29, 2026 02:15:37 UTC
3/54/52/52/55/53/5
Quality
Winner5 of 5
- GPT-6 Luna5of 5
- Composer 2.54of 5
- Claude Sonnet 5.5 via Cursor3of 5
- GPT-6 Sol3of 5
- Grok 4.7 via Cursor2of 5
- DeepSeek Flash2of 5
-
View Quality battle, Sep 29, 2026 00:11:51 UTC
3/53/52/53/55/55/5
Quality
Winners5 of 5
- GPT-6 Sol5of 5
- Grok 4.75of 5
- Composer 2.53of 5
- Grok 4.7 via Cursor3of 5
- GPT-6 Luna3of 5
- DeepSeek Flash2of 5
-
View Quality battle, Sep 28, 2026 09:13:21 UTC
4/ 5DeepSeek FlashVS2/ 5Qwen 3.7 Flashvia OpenRouter
Quality
Winner4 of 5
- DeepSeek Flash4of 5
- Qwen 3.7 Flash via OpenRouter2of 5
-
View Quality battle, Sep 28, 2026 09:08:09 UTC
3/ 5DeepSeek FlashVS2/ 5Qwen 3.7 Flashvia OpenRouter
Quality
Winner3 of 5
- DeepSeek Flash3of 5
- Qwen 3.7 Flash via OpenRouter2of 5
-
View Quality battle, Sep 28, 2026 06:46:04 UTC
4/54/54/54/55/5
Quality
Winner5 of 5
- GPT-6 Sol5of 5
- Composer 2.54of 5
- Grok 4.7 via Cursor4of 5
- DeepSeek Flash4of 5
- GPT-6 Luna4of 5
-
View Quality battle, Sep 28, 2026 01:56:26 UTC
5/55/55/51/55/55/5
Quality
Winners5 of 5
- Composer 2.55of 5
- Grok 4.7 via Cursor5of 5
- DeepSeek Flash5of 5
- GPT-6 Luna5of 5
- GPT-6 Sol5of 5
- Kimi K3 via NVIDIA1of 5
-
View Quality battle, Sep 27, 2026 21:37:30 UTC
4/54/55/54/55/54/5
Quality
Winners5 of 5
- DeepSeek Flash5of 5
- GPT-5.6 Sol5of 5
- Composer 2.54of 5
- Grok 4.7 via Cursor4of 5
- Kimi K3 via NVIDIA4of 5
- GPT-6 Luna4of 5
-
View Quality battle, Sep 27, 2026 21:36:38 UTC
3/55/52/52/52/53/5
Quality
Winner5 of 5
- Grok 4.7 via Cursor5of 5
- Composer 2.53of 5
- GPT-6 Luna3of 5
- DeepSeek Flash2of 5
- Kimi K3 via NVIDIA2of 5
- GPT-5.6 Sol2of 5
-
View Quality battle, Sep 27, 2026 18:05:31 UTC
3/54/52/51/53/55/5
Quality
Winner5 of 5
- GPT-6 Luna5of 5
- Grok 4.7 via Cursor4of 5
- Composer 2.53of 5
- GPT-5.6 Sol3of 5
- DeepSeek Flash2of 5
- Kimi K3 via NVIDIA1of 5
-
View Quality battle, Sep 27, 2026 17:09:28 UTC
5/54/55/54/54/54/5
Quality
Winners5 of 5
- Composer 2.55of 5
- DeepSeek Flash5of 5
- Grok 4.7 via Cursor4of 5
- Kimi K3 via NVIDIA4of 5
- GPT-5.6 Sol4of 5
- GPT-6 Luna4of 5
-
View Quality battle, Sep 27, 2026 16:57:36 UTC
3/54/52/53/55/54/5
Quality
Winner5 of 5
- GPT-5.6 Sol5of 5
- Grok 4.7 via Cursor4of 5
- GPT-6 Luna4of 5
- Composer 2.53of 5
- Kimi K3 via NVIDIA3of 5
- DeepSeek Flash2of 5
-
View Quality battle, Sep 27, 2026 05:39:03 UTC
5/54/55/53/54/54/5
Quality
Winners5 of 5
- Composer 2.55of 5
- DeepSeek Flash5of 5
- Grok 4.7 via Cursor4of 5
- GPT-5.6 Sol4of 5
- GPT-6 Luna4of 5
- Kimi K3 via NVIDIA3of 5
-
View Quality battle, Sep 27, 2026 03:53:33 UTC
3/53/52/55/53/5
Quality
Winner5 of 5
- GPT-5.6 Sol5of 5
- Composer 2.53of 5
- Grok 4.7 via Cursor3of 5
- GPT-6 Luna3of 5
- DeepSeek Flash2of 5
-
View Quality battle, Sep 26, 2026 04:53:39 UTC
4/55/54/55/52/54/5
Quality
Winners5 of 5
- Grok 4.7 via Cursor5of 5
- GPT-6 Luna5of 5
- Composer 2.54of 5
- DeepSeek Flash4of 5
- Grok 4.74of 5
- Qwen 3.8 Flash via OpenRouter2of 5
-
View Quality battle, Sep 25, 2026 21:55:38 UTC
3/54/53/54/52/54/5
Quality
Winners4 of 5
- Grok 4.7 via Cursor4of 5
- GPT-6 Luna4of 5
- Grok 4.74of 5
- Composer 2.53of 5
- DeepSeek Flash3of 5
- Qwen 3.8 Flash via OpenRouter2of 5
-
View Quality battle, Sep 25, 2026 21:02:53 UTC
5/54/54/53/54/5
Quality
Winner5 of 5
- Composer 2.55of 5
- Grok 4.7 via Cursor4of 5
- DeepSeek Flash4of 5
- Qwen 3.8 Flash via OpenRouter4of 5
- GPT-6 Luna3of 5
-
View Quality battle, Sep 25, 2026 16:16:34 UTC
5/54/52/54/53/54/5+1
Quality
Winner5 of 5
- Claude Opus 5.5 via Cursor5of 5
- Claude Sonnet 5 via Cursor4of 5
- Grok 4.7 via Cursor4of 5
- GPT-6 Luna4of 5
- DeepSeek Flash3of 5
- Qwen 3.8 Flash via OpenRouter3of 5
- Composer 2.52of 5
-
View Quality battle, Sep 25, 2026 04:35:44 UTC
5/53/55/54/53/54/5+5
Quality
Winners5 of 5
- Claude Opus 5.5 via Cursor5of 5
- Composer 2.55of 5
- GPT-6 Sol5of 5
- Grok 4.7 via Cursor4of 5
- Kimi K3 via NVIDIA4of 5
- GPT-6 Luna4of 5
- Grok 4.74of 5
- Claude Sonnet 5 via Cursor3of 5
- DeepSeek Flash3of 5
- GPT-5.6 Terra3of 5
- Qwen 3.8 Flash via OpenRouter3of 5
-
View Quality battle, Sep 25, 2026 02:12:24 UTC
4/54/54/54/54/53/5+2
Quality
Winner5 of 5
- Grok 4.75of 5
- Claude Opus 5.5 via Cursor4of 5
- Claude Sonnet 5 via Cursor4of 5
- Composer 2.54of 5
- Grok 4.7 via Cursor4of 5
- DeepSeek Flash4of 5
- Qwen 3.8 Flash via OpenRouter4of 5
- GPT-6 Luna3of 5
-
View Quality battle, Sep 24, 2026 23:57:35 UTC
5/54/53/53/52/52/5+1
Quality
Winner5 of 5
- Claude Opus 5.5 via Cursor5of 5
- Claude Sonnet 5 via Cursor4of 5
- Composer 2.53of 5
- Grok 4.7 via Cursor3of 5
- Grok 4.73of 5
- DeepSeek Flash2of 5
- GPT-6 Luna2of 5
-
View Quality battle, Sep 24, 2026 17:35:40 UTC
4/53/51/54/52/54/5
Quality
Winners4 of 5
- Composer 2.54of 5
- GPT-6 Luna4of 5
- Grok 4.74of 5
- DeepSeek Flash3of 5
- Qwen 3.7 Flash via OpenRouter2of 5
- Nemotron 3.5 Lightning 30B A3B1of 5
-
View Quality battle, Sep 24, 2026 02:33:13 UTC
5/51/54/55/5
Quality
Winners5 of 5
- Composer 2.55of 5
- Grok 4.75of 5
- GPT-6 Luna4of 5
- Nemotron 3.5 Lightning 30B A3B1of 5
-
View Quality battle, Sep 24, 2026 02:05:40 UTC
5/53/52/54/54/5
Quality
Winner5 of 5
- Composer 2.55of 5
- GPT-6 Luna4of 5
- Grok 4.74of 5
- DeepSeek Flash3of 5
- Nemotron 3.5 Lightning 30B A3B2of 5
-
View Quality battle, Sep 23, 2026 18:13:33 UTC
4/53/52/55/5
Quality
Winner5 of 5
- Grok 4.75of 5
- DeepSeek Flash4of 5
- Nemotron 3.5 Lightning 30B A3B3of 5
- Qwen 3.7 Flash via OpenRouter2of 5
-
View Quality battle, Sep 23, 2026 14:14:08 UTC
4/54/55/5
Quality
Winner5 of 5
- Grok 4.75of 5
- Composer 2.54of 5
- GPT-6 Luna4of 5
-
View Quality battle, Sep 23, 2026 06:54:52 UTC
4/ 5GPT-6 LunaVS4/ 5Grok 4.7
Quality
Winners4 of 5
- GPT-6 Luna4of 5
- Grok 4.74of 5
-
View Quality battle, Sep 21, 2026 14:31:07 UTC
5/ 5DeepSeek FlashVS5/ 5GPT-5.6 Luna
Quality
Winners5 of 5
- DeepSeek Flash5of 5
- GPT-5.6 Luna5of 5
-
View Quality battle, Sep 21, 2026 02:51:13 UTC
4/55/54/54/55/55/5+1
Quality
Winners5 of 5
- Grok 4.6 via Cursor5of 5
- GPT-5.6 Sol5of 5
- GPT-5.6 Terra5of 5
- Grok 4.65of 5
- Composer 2.54of 5
- DeepSeek Flash4of 5
- GPT-5.6 Luna4of 5
-
View Quality battle, Sep 21, 2026 01:29:47 UTC
4/55/55/53/55/55/5+1
Quality
Winners5 of 5
- Grok 4.6 via Cursor5of 5
- DeepSeek Flash5of 5
- GPT-5.6 Sol5of 5
- GPT-5.6 Terra5of 5
- Composer 2.54of 5
- GPT-5.6 Luna3of 5
- Grok 4.63of 5
-
View Quality battle, Sep 20, 2026 23:56:48 UTC
4/54/54/53/55/55/5+1
Quality
Winners5 of 5
- GPT-5.6 Sol5of 5
- GPT-5.6 Terra5of 5
- Composer 2.54of 5
- Grok 4.6 via Cursor4of 5
- DeepSeek Flash4of 5
- Grok 4.64of 5
- GPT-5.6 Luna3of 5
-
View Quality battle, Sep 20, 2026 22:11:19 UTC
3/55/54/55/55/55/5+1
Quality
Winners5 of 5
- Grok 4.6 via Cursor5of 5
- GPT-5.6 Luna5of 5
- GPT-5.6 Sol5of 5
- GPT-5.6 Terra5of 5
- DeepSeek Flash4of 5
- Grok 4.64of 5
- Composer 2.53of 5
-
View Quality battle, Sep 20, 2026 17:13:48 UTC
4/53/54/53/55/54/5+1
Quality
Winner5 of 5
- GPT-5.6 Sol5of 5
- Composer 2.54of 5
- DeepSeek Flash4of 5
- GPT-5.6 Terra4of 5
- Grok 4.6 via Cursor3of 5
- GPT-5.6 Luna3of 5
- Grok 4.63of 5
-
View Quality battle, Sep 20, 2026 17:01:57 UTC
4/54/54/55/55/54/5+1
Quality
Winners5 of 5
- GPT-5.6 Luna5of 5
- GPT-5.6 Sol5of 5
- Composer 2.54of 5
- Grok 4.6 via Cursor4of 5
- DeepSeek Flash4of 5
- GPT-5.6 Terra4of 5
- Grok 4.64of 5
-
View Quality battle, Sep 20, 2026 07:50:18 UTC
3/53/54/55/54/55/5+2
Quality
Winners5 of 5
- DeepSeek Flash5of 5
- GPT-5.6 Sol5of 5
- Grok 4.6 via Cursor4of 5
- GPT-5.6 Luna4of 5
- GPT-5.6 Terra4of 5
- Grok 4.64of 5
- Claude Sonnet 5 via Cursor3of 5
- Composer 2.53of 5
-
View Quality battle, Sep 20, 2026 05:23:34 UTC
5/54/55/54/54/5
Quality
Winners5 of 5
- DeepSeek Flash5of 5
- GPT-5.6 Sol5of 5
- GPT-5.6 Luna4of 5
- GPT-5.6 Terra4of 5
- Grok 4.64of 5
-
View Quality battle, Sep 20, 2026 04:02:58 UTC
4/ 5DeepSeek FlashVS4/ 5Qwen 3.7 Flashvia OpenRouter
Quality
Winners4 of 5
- DeepSeek Flash4of 5
- Qwen 3.7 Flash via OpenRouter4of 5
-
View Quality battle, Sep 20, 2026 03:10:58 UTC
4/ 5DeepSeek FlashVS3/ 5Qwen 3.7 Flashvia OpenRouter
Quality
Winner4 of 5
- DeepSeek Flash4of 5
- Qwen 3.7 Flash via OpenRouter3of 5
-
View Quality battle, Sep 20, 2026 02:48:00 UTC
4/53/54/54/5
Quality
Winners4 of 5
- DeepSeek Flash4of 5
- Qwen 3.7 Flash via OpenRouter4of 5
- Grok 4.64of 5
- GPT-5.6 Sol3of 5
-
View Quality battle, Sep 19, 2026 23:46:58 UTC
4/ 5Composer 2.5VS5/ 5GPT-5.6 Sol
Quality
Winner5 of 5
- GPT-5.6 Sol5of 5
- Composer 2.54of 5
-
View Quality battle, Sep 19, 2026 21:20:43 UTC
3/54/53/55/54/5
Quality
Winner5 of 5
- GPT-5.6 Sol5of 5
- Grok 4.6 via Cursor4of 5
- GPT-5.6 Terra4of 5
- Composer 2.53of 5
- GPT-5.6 Luna3of 5
Difficulty is published only when every score in the battle recorded the same low, medium, high, or critical label. Otherwise it is not recorded. Prompts and code are not published.