Who is SOTA in Coding?Claude Opus 5.5 & Claude Sonnet 5.5
Software engineering skill. Terminal-Bench 4.0 and SWE-bench Pro V2 HARD are the primaries. SWE-bench Verified is shown and ignored for the crown. As of Nov 6, 2026, Claude Opus 5.5 & Claude Sonnet 5.5 are tied for state of the art in Coding (since… Crown history, benchmark weights and methodology.
| # | Model | State | Confidence |
|---|---|---|---|
| 1 | AClaude Opus 5.5 Anthropic | Co-SOTA · Coding | medium |
| 1 | AClaude Sonnet 5.5 Anthropic | Co-SOTA · Coding | medium |
| 2 | OGPT-6 Astra OpenAI | Near-SOTA · Coding | medium |
| 3 | OGPT-6.1 Sol OpenAI | Near-SOTA · Coding | medium |
| 4 | MMuse Wonder Meta | #4 in Coding | medium |
| 5 | AClaude Fable 5.1 Anthropic | #5 in Coding | medium |
| 6 | GGemini 4 Argon Google DeepMind | #6 in Coding | medium |
| 7 | AClaude Opus 5 Anthropic | #7 in Coding | medium |
| 8 | DSDeepSeek V4.1 Flash 1017 DeepSeek | #8 in Coding | medium |
| 9 | OGPT-6 Sol OpenAI | #9 in Coding | medium |
| 10 | MMuse Wonder Full Meta | #10 in Coding | medium |
| 11 | AClaude Fable 5 Anthropic | #11 in Coding | medium |
| 12 | DSDeepSeek V4.1 Flash DeepSeek | #12 in Coding | medium |
| 13 | ZGLM 5.3 Zhipu AI | #13 in Coding | medium |
| 14 | xGrok 4.7 xAI | #14 in Coding | medium |
Badges for the leaders
[](https://isitsota.com/m/claude-opus-5-5)
<a href="https://isitsota.com/m/claude-opus-5-5"><img alt="CO-SOTA · Coding · Oct 2026" src="https://isitsota.com/badge/claude-opus-5-5/coding.svg" height="28"></a>
[](https://isitsota.com/m/claude-sonnet-5-5)
<a href="https://isitsota.com/m/claude-sonnet-5-5"><img alt="CO-SOTA · Coding · Oct 2026" src="https://isitsota.com/badge/claude-sonnet-5-5/coding.svg" height="28"></a>
Not enough data yet
Gemini 4 Carbon — #1 on LMArena Text (style-controlled, coding); missing Terminal-Bench 4.0 and SWE-bench Pro V2 HARD
Claude Opus 4.7 — #2 on LMArena Text (style-controlled, coding); missing Terminal-Bench 4.0 and SWE-bench Pro V2 HARD
Claude Opus 4.6 — #6 on LMArena Text (style-controlled, coding); missing Terminal-Bench 4.0 and SWE-bench Pro V2 HARD
Muse Spark 1.2 — #8 on LMArena Text (style-controlled, coding); missing Terminal-Bench 4.0 and SWE-bench Pro V2 HARD
Claude Haiku 4.5 — #12 on SWE-bench Pro V2 HARD; missing Terminal-Bench 4.0 and LMArena Text (style-controlled, coding)
Muse Spark 1.1 — #17 on LMArena Text (style-controlled, coding); missing Terminal-Bench 4.0 and SWE-bench Pro V2 HARD
Claude Opus 4.5 — #19 on LMArena Text (style-controlled, coding); missing Terminal-Bench 4.0 and SWE-bench Pro V2 HARD
Muse Spark — #22 on LMArena Text (style-controlled, coding); missing Terminal-Bench 4.0 and SWE-bench Pro V2 HARD
Claude Sonnet 4.6 — #23 on LMArena Text (style-controlled, coding); missing Terminal-Bench 4.0 and SWE-bench Pro V2 HARD
Qwen3 8 — #25 on LMArena Text (style-controlled, coding); missing Terminal-Bench 4.0 and SWE-bench Pro V2 HARD
Qwen3 7 Max Preview — #26 on LMArena Text (style-controlled, coding); missing Terminal-Bench 4.0 and SWE-bench Pro V2 HARD
Gemini 3.1 Pro Preview — #28 on LMArena Text (style-controlled, coding); missing Terminal-Bench 4.0 and SWE-bench Pro V2 HARD
Mimo V2.5 Pro — #29 on LMArena Text (style-controlled, coding); missing Terminal-Bench 4.0 and SWE-bench Pro V2 HARD
GPT-5.4 — #30 on LMArena Text (style-controlled, coding); missing Terminal-Bench 4.0 and SWE-bench Pro V2 HARD
GPT-5.5 — #35 on LMArena Text (style-controlled, coding); missing Terminal-Bench 4.0 and SWE-bench Pro V2 HARD
Claude Sonnet 4.5 — #36 on LMArena Text (style-controlled, coding); missing Terminal-Bench 4.0 and SWE-bench Pro V2 HARD
Gemini 3.6 Flash — #37 on LMArena Text (style-controlled, coding); missing Terminal-Bench 4.0 and SWE-bench Pro V2 HARD
Gemini 3 Pro — #39 on LMArena Text (style-controlled, coding); missing Terminal-Bench 4.0 and SWE-bench Pro V2 HARD
Kimi K2 6 — #40 on LMArena Text (style-controlled, coding); missing Terminal-Bench 4.0 and SWE-bench Pro V2 HARD
GPT-5.2 Chat — #41 on LMArena Text (style-controlled, coding); missing Terminal-Bench 4.0 and SWE-bench Pro V2 HARD
GLM 5.2 — #42 on LMArena Text (style-controlled, coding); missing Terminal-Bench 4.0 and SWE-bench Pro V2 HARD
Dola Seed 2.0 Pro — #44 on LMArena Text (style-controlled, coding); missing Terminal-Bench 4.0 and SWE-bench Pro V2 HARD
GPT-5.5 Instant — #45 on LMArena Text (style-controlled, coding); missing Terminal-Bench 4.0 and SWE-bench Pro V2 HARD
Qwen3 5 Max Preview — #46 on LMArena Text (style-controlled, coding); missing Terminal-Bench 4.0 and SWE-bench Pro V2 HARD
GLM 5.1 — #47 on LMArena Text (style-controlled, coding); missing Terminal-Bench 4.0 and SWE-bench Pro V2 HARD
Ernie 5.1 — #48 on LMArena Text (style-controlled, coding); missing Terminal-Bench 4.0 and SWE-bench Pro V2 HARD
Qwen3 6 Max Preview — #49 on LMArena Text (style-controlled, coding); missing Terminal-Bench 4.0 and SWE-bench Pro V2 HARD
Claude Opus 4.1 — #50 on LMArena Text (style-controlled, coding); missing Terminal-Bench 4.0 and SWE-bench Pro V2 HARD
Grok 4.20 Beta — #51 on LMArena Text (style-controlled, coding); missing Terminal-Bench 4.0 and SWE-bench Pro V2 HARD
Grok 4.20 Multi Agent Beta — #54 on LMArena Text (style-controlled, coding); missing Terminal-Bench 4.0 and SWE-bench Pro V2 HARD
Gemini 3.5 Flash — #55 on LMArena Text (style-controlled, coding); missing Terminal-Bench 4.0 and SWE-bench Pro V2 HARD
Grok 4.20 Beta 1 — #56 on LMArena Text (style-controlled, coding); missing Terminal-Bench 4.0 and SWE-bench Pro V2 HARD
Gemini 3 Flash — #59 on LMArena Text (style-controlled, coding); missing Terminal-Bench 4.0 and SWE-bench Pro V2 HARD
Beam 1.0 501B A23b — #60 on LMArena Text (style-controlled, coding); missing Terminal-Bench 4.0 and SWE-bench Pro V2 HARD
DeepSeek V4 Pro — #61 on LMArena Text (style-controlled, coding); missing Terminal-Bench 4.0 and SWE-bench Pro V2 HARD
Kimi K2 5 — #62 on LMArena Text (style-controlled, coding); missing Terminal-Bench 4.0 and SWE-bench Pro V2 HARD
Hy3 — #63 on LMArena Text (style-controlled, coding); missing Terminal-Bench 4.0 and SWE-bench Pro V2 HARD
Mimo V2 Pro — #64 on LMArena Text (style-controlled, coding); missing Terminal-Bench 4.0 and SWE-bench Pro V2 HARD
Gemma 4 31B — #65 on LMArena Text (style-controlled, coding); missing Terminal-Bench 4.0 and SWE-bench Pro V2 HARD
Gemini 3.5 Flash Lite — #66 on LMArena Text (style-controlled, coding); missing Terminal-Bench 4.0 and SWE-bench Pro V2 HARD
Longcat Flash Chat Exp — #68 on LMArena Text (style-controlled, coding); missing Terminal-Bench 4.0 and SWE-bench Pro V2 HARD
Qwen3 7 Plus — #69 on LMArena Text (style-controlled, coding); missing Terminal-Bench 4.0 and SWE-bench Pro V2 HARD
Grok 4.1 — #70 on LMArena Text (style-controlled, coding); missing Terminal-Bench 4.0 and SWE-bench Pro V2 HARD
Claude Opus 4 — #71 on LMArena Text (style-controlled, coding); missing Terminal-Bench 4.0 and SWE-bench Pro V2 HARD
Qwen3.8 27B — #72 on LMArena Text (style-controlled, coding); missing Terminal-Bench 4.0 and SWE-bench Pro V2 HARD
GLM 5 — #73 on LMArena Text (style-controlled, coding); missing Terminal-Bench 4.0 and SWE-bench Pro V2 HARD
GPT-5.3 Chat — #74 on LMArena Text (style-controlled, coding); missing Terminal-Bench 4.0 and SWE-bench Pro V2 HARD
Mistral Large 4 — #75 on LMArena Text (style-controlled, coding); missing Terminal-Bench 4.0 and SWE-bench Pro V2 HARD
Qwen3 6 Plus — #76 on LMArena Text (style-controlled, coding); missing Terminal-Bench 4.0 and SWE-bench Pro V2 HARD
GPT-5.4 Mini — #78 on LMArena Text (style-controlled, coding); missing Terminal-Bench 4.0 and SWE-bench Pro V2 HARD
GPT-5.1 — #81 on LMArena Text (style-controlled, coding); missing Terminal-Bench 4.0 and SWE-bench Pro V2 HARD
Qwen3.5 397B A17B — #82 on LMArena Text (style-controlled, coding); missing Terminal-Bench 4.0 and SWE-bench Pro V2 HARD
Mimo V2.5 — #83 on LMArena Text (style-controlled, coding); missing Terminal-Bench 4.0 and SWE-bench Pro V2 HARD
Ernie 5.0 — #84 on LMArena Text (style-controlled, coding); missing Terminal-Bench 4.0 and SWE-bench Pro V2 HARD
GPT-5.2 — #85 on LMArena Text (style-controlled, coding); missing Terminal-Bench 4.0 and SWE-bench Pro V2 HARD
Mimo V2 Omni — #87 on LMArena Text (style-controlled, coding); missing Terminal-Bench 4.0 and SWE-bench Pro V2 HARD
DeepSeek V4 Pro Preview — #88 on LMArena Text (style-controlled, coding); missing Terminal-Bench 4.0 and SWE-bench Pro V2 HARD
GLM 5V Turbo — #89 on LMArena Text (style-controlled, coding); missing Terminal-Bench 4.0 and SWE-bench Pro V2 HARD
Grok 4.3 — #90 on LMArena Text (style-controlled, coding); missing Terminal-Bench 4.0 and SWE-bench Pro V2 HARD
Kimi K2 Thinking Turbo — #91 on LMArena Text (style-controlled, coding); missing Terminal-Bench 4.0 and SWE-bench Pro V2 HARD
Amazon Nova Experimental Chat — #92 on LMArena Text (style-controlled, coding); missing Terminal-Bench 4.0 and SWE-bench Pro V2 HARD
GLM 4.7 — #93 on LMArena Text (style-controlled, coding); missing Terminal-Bench 4.0 and SWE-bench Pro V2 HARD
DeepSeek V4 Flash — #94 on LMArena Text (style-controlled, coding); missing Terminal-Bench 4.0 and SWE-bench Pro V2 HARD
Gemma 4 26B A4b — #95 on LMArena Text (style-controlled, coding); missing Terminal-Bench 4.0 and SWE-bench Pro V2 HARD
Qwen3 Max Preview — #97 on LMArena Text (style-controlled, coding); missing Terminal-Bench 4.0 and SWE-bench Pro V2 HARD
Minimax M2 7 — #98 on LMArena Text (style-controlled, coding); missing Terminal-Bench 4.0 and SWE-bench Pro V2 HARD
DeepSeek V4 Flash Preview — #99 on LMArena Text (style-controlled, coding); missing Terminal-Bench 4.0 and SWE-bench Pro V2 HARD
Muse Glimmer — #100 on LMArena Text (style-controlled, coding); missing Terminal-Bench 4.0 and SWE-bench Pro V2 HARD
Mistral Medium 3.5 — #101 on LMArena Text (style-controlled, coding); missing Terminal-Bench 4.0 and SWE-bench Pro V2 HARD
DeepSeek V3.2 — #102 on LMArena Text (style-controlled, coding); missing Terminal-Bench 4.0 and SWE-bench Pro V2 HARD
DeepSeek V3.2 Exp — #103 on LMArena Text (style-controlled, coding); missing Terminal-Bench 4.0 and SWE-bench Pro V2 HARD
Claude Sonnet 4 — #104 on LMArena Text (style-controlled, coding); missing Terminal-Bench 4.0 and SWE-bench Pro V2 HARD
Nvidia Nemotron 3 Ultra 550B A55b — #105 on LMArena Text (style-controlled, coding); missing Terminal-Bench 4.0 and SWE-bench Pro V2 HARD
Qwen3 — #106 on LMArena Text (style-controlled, coding); missing Terminal-Bench 4.0 and SWE-bench Pro V2 HARD
Qwen3 235B A22B Instruct — #108 on LMArena Text (style-controlled, coding); missing Terminal-Bench 4.0 and SWE-bench Pro V2 HARD
Longcat Flash Chat — #109 on LMArena Text (style-controlled, coding); missing Terminal-Bench 4.0 and SWE-bench Pro V2 HARD
GPT-5 — #110 on LMArena Text (style-controlled, coding); missing Terminal-Bench 4.0 and SWE-bench Pro V2 HARD
Mistral Large 3 — #111 on LMArena Text (style-controlled, coding); missing Terminal-Bench 4.0 and SWE-bench Pro V2 HARD
Ernie 5.0 Preview — #112 on LMArena Text (style-controlled, coding); missing Terminal-Bench 4.0 and SWE-bench Pro V2 HARD
Kimi K2 Preview — #113 on LMArena Text (style-controlled, coding); missing Terminal-Bench 4.0 and SWE-bench Pro V2 HARD
ChatGPT 4O Latest — #114 on LMArena Text (style-controlled, coding); missing Terminal-Bench 4.0 and SWE-bench Pro V2 HARD
Gemini 2.5 Pro — #115 on LMArena Text (style-controlled, coding); missing Terminal-Bench 4.0 and SWE-bench Pro V2 HARD
DeepSeek R1 0528 — #116 on LMArena Text (style-controlled, coding); missing Terminal-Bench 4.0 and SWE-bench Pro V2 HARD
Qwen3 VL 235B A22B Instruct — #117 on LMArena Text (style-controlled, coding); missing Terminal-Bench 4.0 and SWE-bench Pro V2 HARD
Solar Pro 4 — #118 on LMArena Text (style-controlled, coding); missing Terminal-Bench 4.0 and SWE-bench Pro V2 HARD
GPT-5 Chat — #119 on LMArena Text (style-controlled, coding); missing Terminal-Bench 4.0 and SWE-bench Pro V2 HARD
Grok 4.1 Fast — #120 on LMArena Text (style-controlled, coding); missing Terminal-Bench 4.0 and SWE-bench Pro V2 HARD
o3 — #121 on LMArena Text (style-controlled, coding); missing Terminal-Bench 4.0 and SWE-bench Pro V2 HARD
GPT-5.4 Nano — #122 on LMArena Text (style-controlled, coding); missing Terminal-Bench 4.0 and SWE-bench Pro V2 HARD
DeepSeek V3.1 Terminus — #123 on LMArena Text (style-controlled, coding); missing Terminal-Bench 4.0 and SWE-bench Pro V2 HARD
Qwen3.5 122B A10B — #124 on LMArena Text (style-controlled, coding); missing Terminal-Bench 4.0 and SWE-bench Pro V2 HARD
GLM 4.6 — #125 on LMArena Text (style-controlled, coding); missing Terminal-Bench 4.0 and SWE-bench Pro V2 HARD
GPT-4.5 Preview — #126 on LMArena Text (style-controlled, coding); missing Terminal-Bench 4.0 and SWE-bench Pro V2 HARD
Gemini 3.1 Flash Lite Preview — #127 on LMArena Text (style-controlled, coding); missing Terminal-Bench 4.0 and SWE-bench Pro V2 HARD
Qwen3 Coder 480B A35B Instruct — #128 on LMArena Text (style-controlled, coding); missing Terminal-Bench 4.0 and SWE-bench Pro V2 HARD
Grok 4 Fast — #129 on LMArena Text (style-controlled, coding); missing Terminal-Bench 4.0 and SWE-bench Pro V2 HARD
GPT-4.1 — #130 on LMArena Text (style-controlled, coding); missing Terminal-Bench 4.0 and SWE-bench Pro V2 HARD
DeepSeek V3.1 — #131 on LMArena Text (style-controlled, coding); missing Terminal-Bench 4.0 and SWE-bench Pro V2 HARD
GLM 4.5 — #132 on LMArena Text (style-controlled, coding); missing Terminal-Bench 4.0 and SWE-bench Pro V2 HARD
Nvidia Nemotron 3.5 Super VL 120B A12B — #133 on LMArena Text (style-controlled, coding); missing Terminal-Bench 4.0 and SWE-bench Pro V2 HARD
Mistral Medium 3.1 — #134 on LMArena Text (style-controlled, coding); missing Terminal-Bench 4.0 and SWE-bench Pro V2 HARD
Hy3 Preview — #135 on LMArena Text (style-controlled, coding); missing Terminal-Bench 4.0 and SWE-bench Pro V2 HARD
Claude 3.7 Sonnet — #136 on LMArena Text (style-controlled, coding); missing Terminal-Bench 4.0 and SWE-bench Pro V2 HARD
Qwen3 VL 235B A22B Thinking — #137 on LMArena Text (style-controlled, coding); missing Terminal-Bench 4.0 and SWE-bench Pro V2 HARD
Qwen3.5 27B — #138 on LMArena Text (style-controlled, coding); missing Terminal-Bench 4.0 and SWE-bench Pro V2 HARD
Step 3.5 Flash — #139 on LMArena Text (style-controlled, coding); missing Terminal-Bench 4.0 and SWE-bench Pro V2 HARD
Mimo V2 Flash — #140 on LMArena Text (style-controlled, coding); missing Terminal-Bench 4.0 and SWE-bench Pro V2 HARD
Minimax M2 5 — #141 on LMArena Text (style-controlled, coding); missing Terminal-Bench 4.0 and SWE-bench Pro V2 HARD
Qwen3 Next 80B A3B Instruct — #142 on LMArena Text (style-controlled, coding); missing Terminal-Bench 4.0 and SWE-bench Pro V2 HARD
Qwen3 235B A22B — #143 on LMArena Text (style-controlled, coding); missing Terminal-Bench 4.0 and SWE-bench Pro V2 HARD
DeepSeek R1 — #144 on LMArena Text (style-controlled, coding); missing Terminal-Bench 4.0 and SWE-bench Pro V2 HARD
Trinity Large Preview — #145 on LMArena Text (style-controlled, coding); missing Terminal-Bench 4.0 and SWE-bench Pro V2 HARD
Grok 3 Preview — #146 on LMArena Text (style-controlled, coding); missing Terminal-Bench 4.0 and SWE-bench Pro V2 HARD
Qwen3 235B A22B Thinking — #147 on LMArena Text (style-controlled, coding); missing Terminal-Bench 4.0 and SWE-bench Pro V2 HARD
Qwen3 30B A3B Instruct — #148 on LMArena Text (style-controlled, coding); missing Terminal-Bench 4.0 and SWE-bench Pro V2 HARD
Minimax M2 1 Preview — #149 on LMArena Text (style-controlled, coding); missing Terminal-Bench 4.0 and SWE-bench Pro V2 HARD
Hunyuan Vision 1.5 Thinking — #150 on LMArena Text (style-controlled, coding); missing Terminal-Bench 4.0 and SWE-bench Pro V2 HARD
Claude 3.5 Sonnet — #151 on LMArena Text (style-controlled, coding); missing Terminal-Bench 4.0 and SWE-bench Pro V2 HARD
Qwen3 5 Flash — #152 on LMArena Text (style-controlled, coding); missing Terminal-Bench 4.0 and SWE-bench Pro V2 HARD
Grok 4 — #153 on LMArena Text (style-controlled, coding); missing Terminal-Bench 4.0 and SWE-bench Pro V2 HARD
Qwen3.5 35B A3B — #154 on LMArena Text (style-controlled, coding); missing Terminal-Bench 4.0 and SWE-bench Pro V2 HARD
o3-mini — #155 on LMArena Text (style-controlled, coding); missing Terminal-Bench 4.0 and SWE-bench Pro V2 HARD
o4-mini — #156 on LMArena Text (style-controlled, coding); missing Terminal-Bench 4.0 and SWE-bench Pro V2 HARD
GPT-4.1 Mini — #157 on LMArena Text (style-controlled, coding); missing Terminal-Bench 4.0 and SWE-bench Pro V2 HARD
o1 — #158 on LMArena Text (style-controlled, coding); missing Terminal-Bench 4.0 and SWE-bench Pro V2 HARD
Mistral Medium 3 — #159 on LMArena Text (style-controlled, coding); missing Terminal-Bench 4.0 and SWE-bench Pro V2 HARD
GPT-5 Mini — #160 on LMArena Text (style-controlled, coding); missing Terminal-Bench 4.0 and SWE-bench Pro V2 HARD
DeepSeek V3 0324 — #161 on LMArena Text (style-controlled, coding); missing Terminal-Bench 4.0 and SWE-bench Pro V2 HARD
Nvidia Nemotron 3.5 Lightning 30B A3B — #162 on LMArena Text (style-controlled, coding); missing Terminal-Bench 4.0 and SWE-bench Pro V2 HARD
Gemini 2.5 Flash Preview — #163 on LMArena Text (style-controlled, coding); missing Terminal-Bench 4.0 and SWE-bench Pro V2 HARD
GLM 4.5 Air — #164 on LMArena Text (style-controlled, coding); missing Terminal-Bench 4.0 and SWE-bench Pro V2 HARD
Gemini 2.5 Flash — #165 on LMArena Text (style-controlled, coding); missing Terminal-Bench 4.0 and SWE-bench Pro V2 HARD
GLM 4.7 Flash — #166 on LMArena Text (style-controlled, coding); missing Terminal-Bench 4.0 and SWE-bench Pro V2 HARD
Qwen3 Next 80B A3B Thinking — #167 on LMArena Text (style-controlled, coding); missing Terminal-Bench 4.0 and SWE-bench Pro V2 HARD
Minimax M1 — #168 on LMArena Text (style-controlled, coding); missing Terminal-Bench 4.0 and SWE-bench Pro V2 HARD
Best page and recent changes
- Coding (best per dollar): Claude Opus 5.5 and Claude Sonnet 5.5 and DeepSeek V4.1 Flash and DeepSeek V4.1 Flash 1017 and Mercury 3 are co-SOTA
- Coding (best per dollar): Claude Opus 5.5 and Claude Sonnet 5.5 and DeepSeek V4.1 Flash and DeepSeek V4.1 Flash 1017 are co-SOTA
- Coding (best per dollar): Claude Opus 5.5 and Claude Sonnet 5.5 and DeepSeek V4.1 Flash and DeepSeek V4.1 Flash 1017 and GLM 5.3 Flash are co-SOTA
What can move this crown
- Terminal-Bench 4.0 — primary, weight 1
- SWE-bench Pro V2 HARD — primary, weight 1
- LMArena Text (style-controlled, coding) — primary, weight 0.6
- Terminal-Bench 2.0 — secondary, weight 0.35
- Aider Polyglot — secondary, weight 0.35
- Code Migration — secondary, weight 0.35 · Source: Vals AI · Automatic (tests or exact checks)
- SWE-bench Verified — display, weight 0 (display only, cannot crown)
Source: Vals AI for the Vals benchmarks above: proprietary private test sets run by Vals and republished with permission. Only each benchmark's standard harness counts; product-harness runs (Claude Code, Codex and similar) are not matched to base models.
Who is SOTA in Coding?
As of Nov 6, 2026, Claude Opus 5.5 & Claude Sonnet 5.5 are tied for state of the art in Coding (since Oct 6, 2026; sources Terminal-Bench 4.0 and Code Migration; methodology v1.0).
Since when is the Coding crown current?
The current crown in Coding has held since Oct 6, 2026.