#评测/基准

真实世界的结果已经出炉。Code Arena 上出现了新的 #1 —— GPT-6 Astra (Max)！ 它还重塑了帕累托前沿，成为每百万 token 40 美元价位上表现最佳的模型，这与最新的 Claude 模型定价相当。 @OpenAI 的 GPT-6 Astra 在 Code Arena: WebDev 中以 1797 分登顶。这比排名第 2 的 Claude Fable 5.1 (Max)（1762 分）领先了整整 +35 分，比排名第 3 的 Claude Opus 5 (Max)（1688 分）也更高。 相比排名第 13 的 GPT-5.6 Sol (xHigh)，这是一次 +180 分的显著提升。 分类级别的投票仍在统计中，但我们已经看到它在以下类别中排名第 1：数据与分析、消费产品、内容创作工具，并在游戏与模拟中排名第 2。 敬请关注其他类别，如品牌与营销、基于参考的设计以及全栈排名。 祝贺 @OpenAI 团队发布这一成果！

GPT Astra just cooked Claude Fable 5.1 — for a lower price! OpenAI just rolled out GPT‑6 Astra — we put it against Anthropic's Fable 5.1 Both models got the same four briefs: Earth colliding with Mars, a tall ship sucked into a giant whirlpool, Godzilla leveling downtown, a mega-tsunami swallowing a city. One self-contained HTML file per scene, one shot, no edits. GPT Astra: 25,159 tokens, $1.67 Claude Fable 5.1: 37,767 tokens, $2.51 both models live on aimlapi[.]com — 1000+ models, one key.

GPT-6 Astra has set a new ECI record, with a score of 169. This is a substantial jump from the prior best (163), but is within our uncertainty range for the reasoning-era ECI trend. Astra also set new records on our math, continual learning, and game-puzzles benchmarks. On our long-horizon coding benchmark, MirrorCode, Astra ranks between Opus 4.7 and Fable 5. OpenAI gave us pre-release access to test Astra. Charts and more details for Astra’s individual benchmark results in the thread.

我们在 WANDR 上评估了 GPT-6 Astra。它以每任务 $11.98 的成本得分 0.682，是我们测试过的所有模型中的最高分。 GPT-6-Astra 比 Fable 5.1 高 13.5%，成本低 6.1%；比 Opus 5 高 27.0%，成本高 3.3%。

GPT-6 Astra debuts on APEX-Agents at #1 on the leaderboard. 🥇 62.4% Mean score (#1) 🥈 46.7% Pass@1 (#2) It leads Fable 5.1 by 0.4 points on mean score and trails it by 0.8 on Pass@1. APEX-Agents runs long-horizon tasks written by bankers, consultants, and corporate lawyers in our expert network. Against its predecessor GPT-5.6 Sol, Astra moves up 6 places on our leaderboard. It gains 5.7 points on mean and 6.7 on Pass@1. All three domains moved by at least 4.5 points, so this is a broad gain rather than one job pulling the average up. Congratulations to @OpenAI. See full leaderboard: https://www.mercor.com/apex/apex-agents-leaderboard/

fable 5.1 vs fable 5 vs opus 5 – three lord of the rings landmarks, built in 3d from one image the setup: one reference image per scene, one html file per build, everything procedural – no meshes, no textures, no image files, nothing past @threejs from a cdn. each model reads the picture, writes its own prompt from it, then builds to that prompt in the same turn. three named camera shots per scene on keys 1/2/3, so it can be screen-recorded. run through @openrouter tasks: 1. bag end – hobbiton from two frames, outside and in. the round green door has to open onto the room you are standing in 2. barad-dûr – the tower and orodruin from one film still. the eye has to move and track the camera, the volcano erupts on a cycle, the clouds never stop 3. rivendell – jerry vanderstelt's painting. sun shafts that shimmer, water that falls without a break, trees that sway on a gust models: @anthropicai fable 5.1, fable 5, opus 5 total cost, three builds #1 fable 5 – $14.97 #2 opus 5 – $18.53 #3 fable 5.1 – $22.38 wall clock, three builds #1 fable 5 – 38m #2 fable 5.1 – 92m #3 opus 5 – 122m output tokens #1 fable 5 – 298,592 #2 fable 5.1 – 439,435 #3 opus 5 – 724,418 lines of code shipped #1 fable 5 – 2,885 #2 fable 5.1 – 4,021 #3 opus 5 – 5,161 biggest single build, lines #1 opus 5, bag end – 2,410 #2 fable 5.1, barad-dûr – 1,375 #3 fable 5, bag end – 1,319 observations: • fable 5.1 is the only model that furnished the bag end interior – a live fire, panelling, books on the floor, leaded diamond windows, against fable 5's flat color and opus's dark tunnel. the round door outside opens onto that room, the hard part of the brief • what it costs is thinking room. the 128k output ceiling is a thinking budget in disguise: fable 5.1 burned 102,116 of it on reasoning and hit the wall mid-file. opus spent 109,241 and hit the same wall. fable 5 spent 61,240 and finished bag end in one call – the only one that did • fable 5.1's first pass is not the finished thing. its barad-dûr came back with three defects you only catch by looking at it – nothing a read of the code would have flagged • it is the best of the three at being corrected. handed a plain list of what was wrong, it returned 32 targeted patches over two rounds, every one applied first try, and it worked out one of the causes itself instead of guessing at constants conclusion: nine scenes, 12,067 lines and 1.46m output tokens for $55.88 all in – and the cheapest model was also the fastest, by 3.2x! follow @thehypedotnews for 24/7 ai news, analysis and breakdowns

Fable 5.1 from @AnthropicAI on ARC-AGI (Verified): - ARC-AGI-2: 90.0%, $3.12/task - ARC-AGI-1: 97.5%, $1.40/task Across the two benchmarks, Fable 5.1's average cost per task is about 32% lower than Fable 5's, driven by better token efficiency.

Fable 5.1 charges 6× more than GPT-5.6 Sol anthropic's Fable 5.1 went live. we threw it straight at openai's GPT-5.6 Sol. same prompts, one shot. the test: five self-contained three.js scenes, one continuous project — a futuristic mansion on a private island. exterior orbit, grand hall with a diamond chandelier, pool with a water park, garage with 10 lambos, helicopter landing on the roof cost: Claude Fable 5.1 — $5.69 GPT-5.6 Sol — $0.88 what we saw: • fable goes for realism — waves, depth, a sand ring around the island. sol goes low-poly and clean, and its style never breaks across all 5 scenes • fable's chandelier is thousands of individual crystals. sol's hall is honestly just a staircase and a wall • fable's helicopter touches down on the lit helipad much smoother than sol's • fable built a triple-slide water-park tower — and shipped the pool with no water. sol's park is tiny — but the pool is full 6× the price buys you 6× the detail — and the same one-shot bugs. what's your choice? try Fable 5.1 on aimlapi[.]com