Qwen3.5 Flash 02.23

Name: Qwen3.5 Flash 02.23 — independent benchmark scores
Creator: Epoch AI
License: https://creativecommons.org/licenses/by/4.0/

OpenRouterChat1M context· released 2026-02-26Floating alias

openrouter/qwen/qwen3.5-flash-02-23

Estimate cost Compare

Prices as of 2026-07-14 · rev 179affb· unknown is shown as unknown, never $0.00

Value position73rd pctile GPQAno cheaper model matches it on GPQA

Data confidence0/4 exactbenchmarks measured on this exact model · prices 2026-07-14

Cost / request$0.00031K in · 500 out

Input / M$0.10

Output / M$0.40

Context1M1,000,000 tokens

Max output66K65,536 tokens

Capability fingerprint

independent benchmarks, grouped by domain · higher is better · not our measurement

Reasoning

GPQA Diamondgraduate-level science reasoning

78%73rd pctile

family proxyoptimized runEpoch evaluations · Qwen 3.5 Flash (hosted 35B-A3B)

Mathematics

AIME (OTIS mock)olympiad math

86%71st pctile

family proxyoptimized runEpoch evaluations · Qwen 3.5 Flash (hosted 35B-A3B)

FrontierMathresearch-level math

11%67th pctile

family proxyoptimized runEpoch evaluations · Qwen 3.5 Flash (hosted 35B-A3B)

Factuality

SimpleQAfactual accuracy (higher = fewer hallucinations)

20%10th pctile

family proxyEpoch evaluations · Qwen 3.5 Flash (hosted 35B-A3B)

peer median · percentile ranks this model among distinct comparable models (deduped — one entry per model, not per provider) scored on that benchmark · exact model / family proxy per row.

Source: Epoch AI — “AI Benchmarking Hub” (epoch.ai), CC-BY (Epoch AI). Some rows carry an upstream leaderboard (shown per row); Aider & Terminal-Bench are additionally Apache-2.0. Each benchmark measures a different thing on a different scale — rows are not comparable across domains, and a score is not a guarantee of quality on your task.

Human preference (LMArena)

blind pairwise human votes · Elo · style-controlled · not a correctness score

exact modelmeasured on qwen3.5-flashstatistically tied with 13 models overall

Each dot is Qwen3.5 Flash 02.23's Arena score in that category; the whisker is the 95% CI; the firm tick is the peer median across distinct models; faint ticks are the field. This is human preference — which answer people pick in a blind A/B — not a correctness or capability score, and adjacent ranks routinely overlap within their intervals.

Source: LMArena (LMArena Leaderboard (lmarena.ai) — lmarena-ai/leaderboard-dataset on Hugging Face, CC BY 4.0.). Ratings are the style-controlled estimates (length/formatting confound removed), as of 2026-07-27.

Cost vs quality

where Qwen3.5 Flash 02.23 sits among GPQA-scored models

Each dot is a model with a GPQA Diamond score, priced at a 1K-in / 500-out request; Qwen3.5 Flash 02.23 is highlighted. The shaded corner holds models that are both cheaper and higher-scoring; the dashed staircase is the value frontier. Hover any dot for its model.

Also worth considering

cheaper models that score about as well — pick the benchmark that matters to you

1 cheaper model scores within 3 points of Qwen3.5 Flash 02.23 on AIME (OTIS mock).

Model	AIME (OTIS mock)	Cost / req	Savings
NOGPT Oss 120b	89%+3	$0.000175	−42%

Deduped to one entry per model (cheapest offering), priced at the reference 1K-in / 500-out request. Filtered only on the benchmark score — a model with an unknown capability is never silently excluded. A lower price is only cheaper if quality holds on your task — that's what routing proves.

Pricing

Input · fresh prompt tokens	$0.10 / M
Output · generated tokens	$0.40 / M
Cache read · cached-input hit	unknown
Cache write · cache creation	unknown
Reasoning · thinking tokens	unknown

Reasoning tokens: no separate rate is published. Providers typically bill thinking tokens at the output rate ($0.40 / M) — which is what the estimator assumes, so an extended-thinking workload isn't silently undercounted.

Model info

Provider: OpenRouter
Catalog key: openrouter/openrouter/qwen/qwen3.5-flash-02-23
Identifier: Floating alias (may re-point over time)
Type: Chat
Max input: 1,000,000 tokens
Max output: 65,536 tokens
Released: 2026-02-26
Knowledge cutoff: unknown
Weights: Open weights
Price snapshot: 2026-07-14 · rev 179affb

Pricing from TokenTriage's resolved price artifact (TokenTriage resolved price artifact (internal/pricing/data/prices.json)); capability + model metadata is third-party (LiteLLM model_prices_and_context_window.json, models.dev). Unknown means unstated, not absent.

Capabilities

3 documented as supported

Input & output

✓Vision

?PDF input

?Audio input

?Audio output

API behaviour

?Streaming

?Structured output

?Prompt caching

✓Reasoning

Agents & tools

✓Function calling

?Parallel tool calls

?Web search

?Computer use

✓ supported ·✕ not supported ·? not documented ·⚠ sources disagree. A models.dev tag means the LiteLLM catalog was silent and an independent source supplied the value (lower confidence); ? is never silently turned into a confident ✕.

Estimate a request

disjoint token buckets · input = fresh (uncached) tokens

Preset

Input tokens

Output tokens

Cached input

Cache write

Reasoning

Requests / month

Cost / request—

Projected / month—

How output length drives the bill

at a 1K-token prompt · cost scales linearly with output

Output tokens overtake input spend at ~250 tokens for this model — past that, generation is your bill, whatever the headline input price says. Computed by the same cost engine as the estimate above.

Compare Qwen3.5 Flash 02.23 with other models →

Route to Qwen3.5 Flash 02.23

OpenAI-compatible · one base URL

curl https://YOUR-TOKENTRIAGE-HOST/v1/chat/completions \
  -H "Authorization: Bearer $TOKENTRIAGE_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "openrouter/openrouter/qwen/qwen3.5-flash-02-23",
    "messages": [{"role": "user", "content": "Hello"}]
  }'from openai import OpenAI

client = OpenAI(
    base_url="https://YOUR-TOKENTRIAGE-HOST/v1",
    api_key="YOUR_TOKENTRIAGE_KEY",
)

resp = client.chat.completions.create(
    model="openrouter/openrouter/qwen/qwen3.5-flash-02-23",
    messages=[{"role": "user", "content": "Hello"}],
)
print(resp.choices[0].message.content)

Point your existing OpenAI client at your TokenTriage host and pass the catalog key as the model. TokenTriage attributes the real cost per request and can route to a cheaper model once it's proven just as good on your traffic.

Data & API

machine-readable · rev 179affb

Pull this model's pricing, capabilities, benchmarks and cross-source provenance programmatically — every field carries the snapshot rev, and unknown is null, never 0. Free to reuse with attribution: benchmarks & Capabilities Index © Epoch AI (CC-BY (Epoch AI)); human-preference Elo © LMArena (CC-BY-4.0); capability & price cross-check via models.dev v2 (MIT) · Portkey (MIT) · TrueFoundry (MIT); open-weights facts via Hugging Face (per-repo license).

openrouter-openrouter-qwen-qwen3-5-flash-02-23.json openrouter-openrouter-qwen-qwen3-5-flash-02-23.csv

A price is a guess until it meets your traffic.

This page tells you what Qwen3.5 Flash 02.23 charges per token. TokenTriage tells you what it costs on your real requests — and cuts the bill only after proving a cheaper model is just as good.

See the product Back to directory