sora
5bb4b75b07
Rename --judge to --judge-model (alias kept) for symmetry with --model
...
Co-Authored-By: Claude <noreply@anthropic.com>
2026-09-10 06:52:31 +00:00
sora
c78b0d6f0f
Add --api-key/--judge-api-key: explicit keys override env resolution, never serialized
...
Explicit key flows only into request headers (adapter attribute / pool
member), so it cannot leak into the spec string, EvalReport, or logs --
verified by scanning a report produced with a sentinel key. Two-key
setups run twice with different --api-key, or use per-host env vars.
Co-Authored-By: Claude <noreply@anthropic.com>
2026-09-10 06:50:18 +00:00
sora
ad1cd18f04
Add --judge-provider flag; document key resolution rules (env per host, judge included)
...
Co-Authored-By: Claude <noreply@anthropic.com>
2026-09-10 06:45:26 +00:00
sora
08605d9ab2
CLI flag symmetry: --judge-api-url split; mock-boxed hyphen names
...
- --judge now accepts a bare model name paired with --judge-api-url,
mirroring --model/--api-url; full legacy specs keep working
(_compose_judge_spec, verified: name+url -> spec, spec passthrough,
empty -> None; end-to-end on simple_qa with a live judge endpoint)
- mock adapter spellings: mock-boxed / mock-oracle / mock-fc preferred,
colon forms still accepted; bare 'mock' stays echo
- fix mock adapter singleton mode pollution: resolve_adapter memoizes
one instance, so mock-boxed then mock in one process leaked the
boxed mode into the echo run -- each mock spec now builds a fresh
instance
- README: mock-boxed in examples, judge flags row updated
Co-Authored-By: Claude <noreply@anthropic.com>
2026-09-10 06:43:27 +00:00
sora
ea93602dfa
Unified, nicer result tables + conda env setup in README
...
- cli: rich Run Summary table for multi-benchmark runs (green/red rows,
fallback to aligned plain text); unified _fmt_score (fractions render
as percentages everywhere -- was 1.0 in summary vs 100.0% in detail);
fix the stray "summary csv -> None/viz/..." print without --out-dir;
summary.md upgraded to a proper table with model/timestamp/ok-count
header -- one table for a whole N-benchmark run
- text renderer: single-bench headline deduped (dataset==recipe) and
compacted to one facts line; adaptive metric-name column (long names
no longer break alignment)
- md_compare: auto-switches to one-row-per-benchmark when comparing
different benchmarks with different metrics; same-bench model
comparison gains baseline delta markers (+/- percentage points)
- README: conda create/activate in the install block
Co-Authored-By: Claude <noreply@anthropic.com>
2026-09-10 06:30:22 +00:00
sora
27cf8b3c7e
Usability round: progress plugin, CLI provider flags, top-level run(), vendored BFCL checker
...
- progress/: Rich per-sample terminal progress plugin (Run Plan panel,
in-flight/rate/ETA bar); shared console + log-through-live to avoid
interleaved writes, rollback() pairs begin_sample on the retry path,
begin moved inside the semaphore (in-flight = actually generating),
graceful degradation when rich is absent
- cli.py: --provider/--api-url/--model composition (openai-chat |
openai-pool), --disable-thinking/--perf/--textools as first-class
flags, per-bench phase lines and done/failed result lines
- __init__: top-level run()/arun() entries (event-loop safe for notebooks)
- third_party/bfcl: vendored official BFCL ast_checker + type mappings
(Apache-2.0, provenance in __init__.py); imports rerouted locally,
underscore_to_dot parameterized; verified bit-identical with the
bfcl-eval package on 100 real rows -- removes the heavy extra
(pinned numpy + cloud SDK wall) from the install path
- runner: progress/status hooks through generate+evaluate, checkpoint
key scheme fix (empty-store falsy bug), tiered retry backoff,
multi-segment pool {range} expansion fix, adapter-instance passthrough
- pyproject: tree_sitter family joins core deps; [bfcl] extra retired
- README: rewritten (zh) -- install/quickstart/flags reference/bench
table/reliability/extension/architecture/validation
Co-Authored-By: Claude <noreply@anthropic.com>
2026-09-10 05:46:45 +00:00
sora
46bef7d3dd
dp4-flash 28-bench alignment: renderer plugin layer, exec_workers, gen_profiles, AIMD pool, BCB/LCB/bfcl/gfc judge fixes
...
Co-Authored-By: Claude <noreply@anthropic.com>
2026-09-08 05:55:04 +00:00
bee997423a
GPQA 0.15->0.55: (1) per-bench prompt_style cot_letter (es GPQA CoT template, matches its 'Think step by step' contract), (2) mcq_letter extractor case-insensitive answer-tail (ANSWER: vs answer), (3) deterministic choice shuffle
2026-08-28 18:01:16 +00:00
60b2bfc0dc
GPQA deterministic per-question choice shuffle (es-adapter parity: sha256(question) seed, position-bias protection) — was fixed-A; lb2 subset grouping aligned to es (length field, 60 samples)
2026-08-28 16:24:11 +00:00
f7c7536400
Fix images_for_samples export (swe prefetch import error)
2026-08-27 15:27:30 +00:00
da989ea665
Align with local evalscope run.py (full read-through): (1) shuffle+seed42 sample selection identical to es _shuffle_in_place -- same exact sample subset both frameworks; (2) official MATH_PROMPT_TEMPLATE CoT boxed suffix on 7 math benches via DatasetSpec.prompt_suffix; (3) per-bench gen_config (temp/max_tokens from dpv4 yaml) on DatasetSpec, default-merged into gen_kwargs
2026-08-27 11:25:17 +00:00
7ce04b8ac6
cmmlu few_shot_num 5->0 (es code default is 0-shot despite docstring claiming 5); 28-bench parity check all green
2026-08-27 06:43:09 +00:00
e11cae038b
Parity pre-flight check (truncation/few-shot/judge/no-think endpoints vs es run.py); bbh few_shot_num=3 fixed (was 0, es/paper default 3-shot CoT)
2026-08-27 06:37:57 +00:00
e32da10ce9
longbench_v2 chain of fixes: reasoning_content output fallback (Qwen3 thinking channel), nothink soft switch /no_think (template-400 immune), truncation input+output budget, adaptive context shrink on server 400 (cross-tokenizer margin, body-aware detection), pool fails over on 4xx
2026-08-27 06:27:59 +00:00
c4473a1e1c
Token-level middle truncation (ported from evalside run.py: head+tail 128k, mrcr message-window); max_input_tokens param; perf fields (ttft/itl/status/retries) verified persisted in checkpoints
2026-08-27 03:23:33 +00:00
3c63338ac1
Excel renderer (xlsxwriter, 4 sheets: Summary dashboard with 21 columns, Perf detail, Categories, Samples drill-down); !perf spec flag; viz --style excel
2026-08-27 02:56:07 +00:00
e77ea4ce5c
!perf spec flag; perf_stats full dashboard columns (success_rate, latency/ttft/tpot mean+P90+P99, tokens mean/total, output TPS, request QPS); summary.csv perf columns aligned
2026-08-27 02:49:55 +00:00
f2a914d0ff
Performance profile: TTFT/ITL via SSE streaming (collect_perf flag), retries/http_status per request, pool success/retry/failure rates, perf_stats aggregator (P50/P95/P99 latency+ttft, tokens, retry_rate) in metric_groups['perf']; verified on fake SSE server
2026-08-27 02:45:51 +00:00
456d304a69
Fix numeric normalization in math_equal: strip $, commas, markdown (**), trailing units ('540 meters') — gsm8k 0.45->0.80 on ladder20 cross-check; winogrande cross-scoring 20/20 agreement (delta = generation variance)
2026-08-26 17:15:13 +00:00
111336cbee
ladder20 complete 28/28 (Qwen3-8B pool): fixes en route — tau2 off-loop executor, double-encoded tool args, shared adapter cache; swe real-model 0.0 (oracle path verified 1.0)
2026-08-26 10:37:54 +00:00
0e1e31ba10
swe_bench_verified end-to-end verified (oracle patch -> official sweb image -> resolved); image naming mapped to local swebench/ set; ladder2 complete 28/28
2026-08-26 06:40:55 +00:00
3d16e9647a
Tool-call parsing: Qwen3 native <tool_call> XML fallback in _parse (parser-agnostic, zero overhead when server converts properly)
2026-08-26 06:29:49 +00:00
7114564301
Multi-endpoint model pool (openai-pool/{lo..hi} round-robin with failover), nothink/textools spec flags (chat_template_kwargs enable_thinking=false; text-protocol tool calls for backends without --enable-auto-tool-choice), global cross-bench queue in ladder runs
2026-08-26 06:26:52 +00:00
f3514d7c08
Fix checkpoint cross-contamination (scope by dataset name from run_eval, not inferred); ladder20 comparison artifacts
2026-08-26 02:24:00 +00:00
78459c974e
tau2 via OFFICIAL engine: self-running env plugin (run_task hook + needs_adapter generic dispatch, no name hardcoding), deep generate() patch, official ToolCall shape, data plugin keeps verbatim Task json, official reward scoring; checkpoint plugin (per-sample resume) + summary csv with time/categories
2026-08-25 11:06:08 +00:00
85dd193bcf
Execution-bench fixes verified on real model: BCB standalone-module + unittest semantics (100%), LCB base64+zlib+pickle private cases + line-normalized runner (100%), code_any def-start heuristic, general_fc should-call-tool semantics (80%), bfcl real-model 51 samples/17 categories (45.1%, multi_turn needs stateful env - known)
2026-08-25 10:48:20 +00:00
1da665fec4
Add --limit-per-task (per-subset cap, evalscope --limit semantics; composable with --limit as intersection); execution-bench parity verified: official human-eval core 5/5 == our docker sandbox on same completions
2026-08-25 05:18:23 +00:00
89e721414f
Simplify install: light deps (datasets/pyarrow/sympy/pylatexenc/numpy/scipy) are DEFAULT; single [bfcl] extra for the heavy official checker
2026-08-25 02:51:55 +00:00
99c9df5412
Unify on-demand install hints to extras names ([all]/[bfcl]); native bfcl fallback carries upgrade hint
2026-08-25 02:49:09 +00:00
d830e08923
Drop logprob scoring path entirely; MCQ = strict-letter generation (evalscope parity 'ANSWER: X'), few-shot defaults stay; fix output.py duplication
2026-08-25 02:26:26 +00:00
a8d3400ed5
Paper-faithful eval: P1 logprob scoring (completions_echo + chat_first_token fallback, sglang top_logprobs parser), few_shot_num dataset defaults (mmlu5/cmmlu5/mmlu_pro5/gsm8k4/math4/drop3), official BBH 3-shot CoT vendored, strict_letter default prompt (evalscope parity), official simpleqa grader prompt
2026-08-25 02:21:59 +00:00
a32d902e94
Comparison-driven fixes: MCQ choices in prompt + letter contract, Answer: suffix for QA, markdown answer cleaning, trivia_qa answer_phrase priority, DROP gold-as-alternatives (OR) official semantics, retry on 5xx, numpy/scipy compat
2026-08-24 15:48:42 +00:00
3d16ab9103
Add SWE-bench single-turn harness (patch apply + FAIL_TO_PASS in official sweb image, sh entries in docker sandbox), bigcodebench official all-libs image, docker default for humaneval/LCB, input truncation (max_input_chars) + context assembly (passage/context), API retry with backoff, judge thread-safe bridge, parquet blob integrity check, summary.csv in out-dir, sandbox prefetch CLI
2026-08-24 08:43:49 +00:00
b2e7133b20
Add sandbox layer (docker exec hard-isolation + serve envs, refcounted acquire/release, atexit teardown, bind-mount sharing) and agent evaluation driver (message pump drive(), Trajectory, bfcl_mock env with official call-sequence scoring, mock:fc oracle); Deployer delegates to sandbox.serve_env; code_any extractor fixes indentation-stripping; CLI --env
2026-08-24 07:11:03 +00:00
6b3bb330c7
Add model layer: async ModelAdapter (openai_compatible + mock) returning structured ModelOutput(text,tool_calls,usage), Deployer registry (vllm/sglang docker-pinned via models.yaml, external), async run_eval generate->score, CLI --model, agent-ready SampleResult.trajectory/env_state, tests
2026-08-24 06:28:00 +00:00
4a15f80897
Add evaluation layer + visualization: extract/score/aggregate plugins, 28 recipes, official-aligned scorers (PRM800K math, DROP Hungarian EM/F1, SimpleQA A/B/C judge), report artifacts, console renderers, CLI eval/viz, regression tests
2026-08-24 06:09:38 +00:00
414a89216c
Unify cache root override: loader.get/set_cache_root as single source, fixes --cache-dir not relocating .raw blobs
2026-08-24 03:37:15 +00:00
f8cd15fea1
EvalHarness data layer: 28 dataset plugins, lazy materialize cache (raw/ + samples.jsonl + meta.json), ModelScope native loader, CLI list/fetch/unload/stats/show
2026-08-24 03:35:11 +00:00
